https://learn.ifs.name/ https://learn.ifs.name/help/ https://learn.ifs.name/b/jm-slp3/ https://learn.ifs.name/p/classics/ https://learn.ifs.name/p/frontier/ https://learn.ifs.name/d/jm-ch01/ https://learn.ifs.name/d/jm-ch01/s/introduction/ https://learn.ifs.name/d/jm-ch01/s/1-1-what-is-a-large-language-model/ https://learn.ifs.name/d/jm-ch01/s/1-2-what-llms-learn-from-token-prediction/ https://learn.ifs.name/d/jm-ch01/s/1-3-neural-networks-and-embeddings/ https://learn.ifs.name/d/jm-ch01/s/1-4-history-of-speech-and-language-processing/ https://learn.ifs.name/d/jm-ch01/s/1-5-linguistic-structure-and-interpretability/ https://learn.ifs.name/d/jm-ch01/s/1-6-how-language-models-are-trained/ https://learn.ifs.name/d/jm-ch01/s/1-7-inference/ https://learn.ifs.name/d/jm-ch01/s/1-8-agents/ https://learn.ifs.name/d/jm-ch01/s/1-9-evaluating-large-language-models/ https://learn.ifs.name/d/jm-ch01/s/1-10-safety-and-alignment/ https://learn.ifs.name/d/jm-ch01/s/1-11-anthropomorphism-and-terminology/ https://learn.ifs.name/d/jm-ch02/ https://learn.ifs.name/d/jm-ch02/s/introduction/ https://learn.ifs.name/d/jm-ch02/s/2-1-words/ https://learn.ifs.name/d/jm-ch02/s/2-2-morphemes-parts-of-words/ https://learn.ifs.name/d/jm-ch02/s/2-3-unicode/ https://learn.ifs.name/d/jm-ch02/s/2-4-subword-tokenization-byte-pair-encoding/ https://learn.ifs.name/d/jm-ch02/s/2-5-corpora/ https://learn.ifs.name/d/jm-ch02/s/2-6-regular-expressions/ https://learn.ifs.name/d/jm-ch02/s/2-7-simple-unix-tools-for-word-tokenization/ https://learn.ifs.name/d/jm-ch02/s/2-8-rule-based-tokenization/ https://learn.ifs.name/d/jm-ch02/s/2-9-minimum-edit-distance/ https://learn.ifs.name/d/jm-ch02/s/historical-notes/ https://learn.ifs.name/d/jm-ch03/ https://learn.ifs.name/d/jm-ch03/s/introduction/ https://learn.ifs.name/d/jm-ch03/s/3-1-n-grams/ https://learn.ifs.name/d/jm-ch03/s/3-2-training-and-test-sets/ https://learn.ifs.name/d/jm-ch03/s/3-3-perplexity/ https://learn.ifs.name/d/jm-ch03/s/3-4-sampling-sentences-from-a-language-model/ https://learn.ifs.name/d/jm-ch03/s/3-5-generalizing-vs-overfitting/ https://learn.ifs.name/d/jm-ch03/s/3-6-smoothing-interpolation-and-backoff/ https://learn.ifs.name/d/jm-ch03/s/3-7-perplexity-and-entropy/ https://learn.ifs.name/d/jm-ch03/s/historical-notes/ https://learn.ifs.name/d/jm-ch04/ https://learn.ifs.name/d/jm-ch04/s/introduction/ https://learn.ifs.name/d/jm-ch04/s/4-1-machine-learning-and-classification/ https://learn.ifs.name/d/jm-ch04/s/4-2-the-sigmoid-function/ https://learn.ifs.name/d/jm-ch04/s/4-3-classification-with-logistic-regression/ https://learn.ifs.name/d/jm-ch04/s/4-4-learning-in-logistic-regression/ https://learn.ifs.name/d/jm-ch04/s/4-5-the-cross-entropy-loss-function/ https://learn.ifs.name/d/jm-ch04/s/4-6-gradient-descent/ https://learn.ifs.name/d/jm-ch04/s/4-7-multinomial-logistic-regression/ https://learn.ifs.name/d/jm-ch04/s/4-8-learning-in-multinomial-logistic-regression/ https://learn.ifs.name/d/jm-ch04/s/4-9-evaluation-precision-recall-f-measure/ https://learn.ifs.name/d/jm-ch04/s/4-10-test-sets-and-cross-validation/ https://learn.ifs.name/d/jm-ch04/s/4-11-statistical-significance-testing/ https://learn.ifs.name/d/jm-ch04/s/4-12-avoiding-harms-in-classification/ https://learn.ifs.name/d/jm-ch04/s/4-13-interpreting-models/ https://learn.ifs.name/d/jm-ch04/s/4-14-regularization/ https://learn.ifs.name/d/jm-ch04/s/4-15-deriving-the-gradient/ https://learn.ifs.name/d/jm-ch04/s/historical-notes/ https://learn.ifs.name/d/jm-ch05/ https://learn.ifs.name/d/jm-ch05/s/introduction/ https://learn.ifs.name/d/jm-ch05/s/5-1-lexical-semantics/ https://learn.ifs.name/d/jm-ch05/s/5-2-vector-semantics-the-intuition/ https://learn.ifs.name/d/jm-ch05/s/5-3-simple-count-based-embeddings/ https://learn.ifs.name/d/jm-ch05/s/5-4-cosine-for-measuring-similarity/ https://learn.ifs.name/d/jm-ch05/s/5-5-word2vec/ https://learn.ifs.name/d/jm-ch05/s/5-6-visualizing-embeddings/ https://learn.ifs.name/d/jm-ch05/s/5-7-semantic-properties-of-embeddings/ https://learn.ifs.name/d/jm-ch05/s/5-8-bias-and-embeddings/ https://learn.ifs.name/d/jm-ch05/s/5-9-evaluating-vector-models/ https://learn.ifs.name/d/jm-ch05/s/historical-notes/ https://learn.ifs.name/d/jm-ch06/ https://learn.ifs.name/d/jm-ch06/s/introduction/ https://learn.ifs.name/d/jm-ch06/s/6-1-units/ https://learn.ifs.name/d/jm-ch06/s/6-2-the-xor-problem/ https://learn.ifs.name/d/jm-ch06/s/6-3-feedforward-neural-networks/ https://learn.ifs.name/d/jm-ch06/s/6-4-feedforward-networks-for-classification/ https://learn.ifs.name/d/jm-ch06/s/6-5-embeddings-as-input-to-neural-classifiers/ https://learn.ifs.name/d/jm-ch06/s/6-6-training-neural-nets/ https://learn.ifs.name/d/jm-ch06/s/historical-notes/ https://learn.ifs.name/d/jm-ch07/ https://learn.ifs.name/d/jm-ch07/s/introduction/ https://learn.ifs.name/d/jm-ch07/s/7-1-attention/ https://learn.ifs.name/d/jm-ch07/s/7-2-transformer-blocks/ https://learn.ifs.name/d/jm-ch07/s/7-3-parallelizing-computation/ https://learn.ifs.name/d/jm-ch07/s/7-4-the-input-token-and-position-embeddings/ https://learn.ifs.name/d/jm-ch07/s/7-5-the-language-modeling-head/ https://learn.ifs.name/d/jm-ch07/s/7-6-decoding/ https://learn.ifs.name/d/jm-ch07/s/7-7-pretraining-transformer-llms/ https://learn.ifs.name/d/jm-ch07/s/7-8-current-models/ https://learn.ifs.name/d/jm-ch07/s/historical-notes/ https://learn.ifs.name/d/jm-ch08/ https://learn.ifs.name/d/jm-ch08/s/introduction/ https://learn.ifs.name/d/jm-ch08/s/8-1-instruction-tuning/ https://learn.ifs.name/d/jm-ch08/s/8-2-parameter-efficient-fine-tuning/ https://learn.ifs.name/d/jm-ch08/s/8-3-learning-from-preferences/ https://learn.ifs.name/d/jm-ch08/s/8-4-alignment-via-preference-based-learning/ https://learn.ifs.name/d/jm-ch09/ https://learn.ifs.name/d/jm-ch09/s/introduction/ https://learn.ifs.name/d/jm-ch09/s/9-1-three-architectures-for-language-models/ https://learn.ifs.name/d/jm-ch09/s/9-2-bidirectional-transformer-encoders/ https://learn.ifs.name/d/jm-ch09/s/9-3-training-bidirectional-encoders/ https://learn.ifs.name/d/jm-ch09/s/9-4-fine-tuning-for-classification/ https://learn.ifs.name/d/jm-ch09/s/9-5-sequence-labeling-named-entity-recognition/ https://learn.ifs.name/d/jm-ch09/s/summary/ https://learn.ifs.name/d/jm-ch10/ https://learn.ifs.name/d/jm-ch10/s/introduction/ https://learn.ifs.name/d/jm-ch10/s/10-1-contextual-embeddings/ https://learn.ifs.name/d/jm-ch10/s/10-2-probing/ https://learn.ifs.name/d/jm-ch10/s/10-3-the-logit-lens/ https://learn.ifs.name/d/jm-ch10/s/10-6-in-context-learning-and-induction-heads/ https://learn.ifs.name/d/jm-ch11/ https://learn.ifs.name/d/jm-ch11/s/introduction/ https://learn.ifs.name/d/jm-ch11/s/11-1-information-retrieval/ https://learn.ifs.name/d/jm-ch11/s/11-2-evaluating-ir-systems/ https://learn.ifs.name/d/jm-ch11/s/11-3-dense-retrieval/ https://learn.ifs.name/d/jm-ch11/s/11-4-retrieval-augmented-generation/ https://learn.ifs.name/d/jm-ch11/s/11-5-datasets/ https://learn.ifs.name/d/jm-ch11/s/11-6-evaluating-question-answering/ https://learn.ifs.name/d/jm-ch11/s/historical-notes/ https://learn.ifs.name/d/jm-ch13/ https://learn.ifs.name/d/jm-ch13/s/introduction/ https://learn.ifs.name/d/jm-ch13/s/13-1-language-divergences-and-typology/ https://learn.ifs.name/d/jm-ch13/s/13-2-mt-using-encoder-decoder/ https://learn.ifs.name/d/jm-ch13/s/13-3-the-encoder-decoder-model/ https://learn.ifs.name/d/jm-ch13/s/13-4-decoding-beam-search/ https://learn.ifs.name/d/jm-ch13/s/13-5-low-resource-translation/ https://learn.ifs.name/d/jm-ch13/s/13-6-mt-evaluation/ https://learn.ifs.name/d/jm-ch13/s/13-7-bias-and-ethical-issues/ https://learn.ifs.name/d/jm-ch13/s/historical-notes/ https://learn.ifs.name/d/jm-ch14/ https://learn.ifs.name/d/jm-ch14/s/introduction/ https://learn.ifs.name/d/jm-ch14/s/14-1-recurrent-neural-networks/ https://learn.ifs.name/d/jm-ch14/s/14-2-rnns-as-language-models/ https://learn.ifs.name/d/jm-ch14/s/14-3-rnns-for-other-nlp-tasks/ https://learn.ifs.name/d/jm-ch14/s/14-4-stacked-and-bidirectional-rnns/ https://learn.ifs.name/d/jm-ch14/s/14-5-the-lstm/ https://learn.ifs.name/d/jm-ch14/s/14-6-common-rnn-architectures/ https://learn.ifs.name/d/jm-ch14/s/14-7-encoder-decoder-with-rnns/ https://learn.ifs.name/d/jm-ch14/s/14-8-attention/ https://learn.ifs.name/d/jm-ch14/s/historical-notes/ https://learn.ifs.name/d/jm-ch15/ https://learn.ifs.name/d/jm-ch15/s/introduction/ https://learn.ifs.name/d/jm-ch15/s/15-1-phonetic-transcription/ https://learn.ifs.name/d/jm-ch15/s/15-1-arpabet-symbols/ https://learn.ifs.name/d/jm-ch15/s/15-2-articulatory-phonetics/ https://learn.ifs.name/d/jm-ch15/s/15-3-prosody/ https://learn.ifs.name/d/jm-ch15/s/15-4-acoustic-phonetics/ https://learn.ifs.name/d/jm-ch15/s/15-5-log-mel-spectrum/ https://learn.ifs.name/d/jm-ch15/s/15-6-mfcc/ https://learn.ifs.name/d/jm-ch15/s/historical-notes/ https://learn.ifs.name/d/jm-ch15/s/exercises/ https://learn.ifs.name/d/jm-ch16/ https://learn.ifs.name/d/jm-ch16/s/introduction/ https://learn.ifs.name/d/jm-ch16/s/16-1-the-asr-task/ https://learn.ifs.name/d/jm-ch16/s/16-2-convolutional-networks/ https://learn.ifs.name/d/jm-ch16/s/16-3-encoder-decoder-asr/ https://learn.ifs.name/d/jm-ch16/s/16-4-hubert-and-k-means/ https://learn.ifs.name/d/jm-ch16/s/16-5-ctc-and-rnn-t/ https://learn.ifs.name/d/jm-ch16/s/16-6-word-error-rate/ https://learn.ifs.name/d/jm-ch16/s/historical-notes/ https://learn.ifs.name/d/jm-ch17/ https://learn.ifs.name/d/jm-ch17/s/introduction/ https://learn.ifs.name/d/jm-ch17/s/17-1-tts-overview/ https://learn.ifs.name/d/jm-ch17/s/17-2-codecs-and-discrete-audio-tokens/ https://learn.ifs.name/d/jm-ch17/s/17-3-vall-e-two-stage-lm-generation/ https://learn.ifs.name/d/jm-ch17/s/17-4-tts-evaluation/ https://learn.ifs.name/d/jm-ch17/s/17-5-other-speech-tasks/ https://learn.ifs.name/d/jm-ch17/s/historical-notes/ https://learn.ifs.name/d/jm-ch18/ https://learn.ifs.name/d/jm-ch18/s/introduction/ https://learn.ifs.name/d/jm-ch18/s/18-1-english-word-classes/ https://learn.ifs.name/d/jm-ch18/s/18-2-part-of-speech-tagging/ https://learn.ifs.name/d/jm-ch18/s/18-3-named-entities/ https://learn.ifs.name/d/jm-ch18/s/18-4-hmm-part-of-speech-tagging/ https://learn.ifs.name/d/jm-ch18/s/18-5-conditional-random-fields/ https://learn.ifs.name/d/jm-ch18/s/18-6-evaluation-of-ner/ https://learn.ifs.name/d/jm-ch18/s/18-7-further-details/ https://learn.ifs.name/d/jm-ch18/s/historical-notes/ https://learn.ifs.name/d/jm-ch19/ https://learn.ifs.name/d/jm-ch19/s/introduction/ https://learn.ifs.name/d/jm-ch19/s/19-1-constituency/ https://learn.ifs.name/d/jm-ch19/s/19-2-context-free-grammars/ https://learn.ifs.name/d/jm-ch19/s/19-3-treebanks/ https://learn.ifs.name/d/jm-ch19/s/19-4-grammar-equivalence-and-normal-form/ https://learn.ifs.name/d/jm-ch19/s/19-5-ambiguity/ https://learn.ifs.name/d/jm-ch19/s/19-6-cky-parsing/ https://learn.ifs.name/d/jm-ch19/s/19-7-span-based-neural-parsing/ https://learn.ifs.name/d/jm-ch19/s/19-8-evaluating-parsers/ https://learn.ifs.name/d/jm-ch19/s/19-9-heads-and-head-finding/ https://learn.ifs.name/d/jm-ch19/s/historical-notes/ https://learn.ifs.name/d/jm-ch20/ https://learn.ifs.name/d/jm-ch20/s/introduction/ https://learn.ifs.name/d/jm-ch20/s/20-1-dependency-relations/ https://learn.ifs.name/d/jm-ch20/s/20-2-transition-based-parsing/ https://learn.ifs.name/d/jm-ch20/s/20-3-graph-based-parsing/ https://learn.ifs.name/d/jm-ch20/s/20-4-evaluation/ https://learn.ifs.name/d/jm-ch20/s/historical-notes/ https://learn.ifs.name/d/jm-ch21/ https://learn.ifs.name/d/jm-ch21/s/introduction/ https://learn.ifs.name/d/jm-ch21/s/21-1-relation-extraction/ https://learn.ifs.name/d/jm-ch21/s/21-2-relation-extraction-algorithms/ https://learn.ifs.name/d/jm-ch21/s/21-3-extracting-events/ https://learn.ifs.name/d/jm-ch21/s/21-4-representing-time/ https://learn.ifs.name/d/jm-ch21/s/21-5-representing-aspect/ https://learn.ifs.name/d/jm-ch21/s/21-6-timebank/ https://learn.ifs.name/d/jm-ch21/s/21-7-automatic-temporal-analysis/ https://learn.ifs.name/d/jm-ch21/s/21-8-template-filling/ https://learn.ifs.name/d/jm-ch21/s/historical-notes/ https://learn.ifs.name/d/jm-ch22/ https://learn.ifs.name/d/jm-ch22/s/introduction/ https://learn.ifs.name/d/jm-ch22/s/22-1-semantic-roles/ https://learn.ifs.name/d/jm-ch22/s/22-2-diathesis-alternations/ https://learn.ifs.name/d/jm-ch22/s/22-3-problems-with-thematic-roles/ https://learn.ifs.name/d/jm-ch22/s/22-4-propbank/ https://learn.ifs.name/d/jm-ch22/s/22-5-framenet/ https://learn.ifs.name/d/jm-ch22/s/22-6-semantic-role-labeling/ https://learn.ifs.name/d/jm-ch22/s/22-7-selectional-restrictions/ https://learn.ifs.name/d/jm-ch22/s/22-8-primitive-decomposition/ https://learn.ifs.name/d/jm-ch22/s/historical-notes/ https://learn.ifs.name/d/jm-ch23/ https://learn.ifs.name/d/jm-ch23/s/introduction/ https://learn.ifs.name/d/jm-ch23/s/23-1-defining-emotion/ https://learn.ifs.name/d/jm-ch23/s/23-2-available-sentiment-and-affect-lexicons/ https://learn.ifs.name/d/jm-ch23/s/23-3-creating-affect-lexicons-by-human-labeling/ https://learn.ifs.name/d/jm-ch23/s/23-4-semi-supervised-induction-of-affect-lexicons/ https://learn.ifs.name/d/jm-ch23/s/23-5-supervised-learning-of-word-sentiment/ https://learn.ifs.name/d/jm-ch23/s/23-6-using-lexicons-for-sentiment-recognition/ https://learn.ifs.name/d/jm-ch23/s/23-7-using-lexicons-for-affect-recognition/ https://learn.ifs.name/d/jm-ch23/s/23-8-lexicon-based-methods-for-entity-centric-affect/ https://learn.ifs.name/d/jm-ch23/s/23-9-connotation-frames/ https://learn.ifs.name/d/jm-ch23/s/historical-notes/ https://learn.ifs.name/d/jm-ch24/ https://learn.ifs.name/d/jm-ch24/s/introduction/ https://learn.ifs.name/d/jm-ch24/s/24-1-coreference-phenomena-linguistic-background/ https://learn.ifs.name/d/jm-ch24/s/24-2-coreference-tasks-and-datasets/ https://learn.ifs.name/d/jm-ch24/s/24-3-mention-detection/ https://learn.ifs.name/d/jm-ch24/s/24-4-architectures-for-coreference-algorithms/ https://learn.ifs.name/d/jm-ch24/s/24-5-classifiers-using-hand-built-features/ https://learn.ifs.name/d/jm-ch24/s/24-6-a-neural-mention-ranking-algorithm/ https://learn.ifs.name/d/jm-ch24/s/24-7-entity-linking/ https://learn.ifs.name/d/jm-ch24/s/24-8-evaluation-of-coreference-resolution/ https://learn.ifs.name/d/jm-ch24/s/24-9-winograd-schema-problems/ https://learn.ifs.name/d/jm-ch24/s/24-10-gender-bias-in-coreference/ https://learn.ifs.name/d/jm-ch24/s/historical-notes/ https://learn.ifs.name/d/jm-ch25/ https://learn.ifs.name/d/jm-ch25/s/introduction/ https://learn.ifs.name/d/jm-ch25/s/25-1-coherence-relations/ https://learn.ifs.name/d/jm-ch25/s/25-2-discourse-structure-parsing/ https://learn.ifs.name/d/jm-ch25/s/25-3-centering-and-entity-based-coherence/ https://learn.ifs.name/d/jm-ch25/s/25-4-representation-learning-models-for-local-coherence/ https://learn.ifs.name/d/jm-ch25/s/25-5-global-coherence/ https://learn.ifs.name/d/jm-ch25/s/historical-notes/ https://learn.ifs.name/d/jm-ch26/ https://learn.ifs.name/d/jm-ch26/s/introduction/ https://learn.ifs.name/d/jm-ch26/s/26-1-properties-of-human-conversation/ https://learn.ifs.name/d/jm-ch26/s/26-2-dialog-acts-and-corpora/ https://learn.ifs.name/d/shannon1948/ https://learn.ifs.name/d/shannon1948/s/introduction/ https://learn.ifs.name/d/shannon1948/s/1-the-discrete-noiseless-channel/ https://learn.ifs.name/d/shannon1948/s/2-the-discrete-source-of-information/ https://learn.ifs.name/d/shannon1948/s/3-the-series-of-approximations-to-english/ https://learn.ifs.name/d/shannon1948/s/4-graphical-representation-of-a-markoff-process/ https://learn.ifs.name/d/shannon1948/s/5-ergodic-and-mixed-sources/ https://learn.ifs.name/d/shannon1948/s/6-choice-uncertainty-and-entropy/ https://learn.ifs.name/d/shannon1948/s/7-the-entropy-of-an-information-source/ https://learn.ifs.name/d/shannon1948/s/8-representation-of-the-encoding-and-decoding-operations/ https://learn.ifs.name/d/shannon1948/s/9-the-fundamental-theorem-for-a-noiseless-channel/ https://learn.ifs.name/d/shannon1948/s/10-discussion-and-examples/ https://learn.ifs.name/d/shannon1948/s/12-equivocation-and-channel-capacity/ https://learn.ifs.name/d/shannon1948/s/13-the-fundamental-theorem-for-a-discrete-channel-with-noise/ https://learn.ifs.name/d/shannon1948/s/14-discussion/ https://learn.ifs.name/d/shannon1948/s/17-an-example-of-efficient-coding/ https://learn.ifs.name/d/shannon1948/s/19-band-limited-ensembles-of-functions/ https://learn.ifs.name/d/shannon1948/s/20-entropy-of-a-continuous-distribution/ https://learn.ifs.name/d/shannon1948/s/25-channel-capacity-with-an-average-power-limitation/ https://learn.ifs.name/d/shannon1948/s/28-the-rate-for-a-source-relative-to-a-fidelity-evaluation/ https://learn.ifs.name/d/turing1950/ https://learn.ifs.name/d/turing1950/s/1-the-imitation-game/ https://learn.ifs.name/d/turing1950/s/2-critique-of-the-new-problem/ https://learn.ifs.name/d/turing1950/s/3-the-machines-concerned-in-the-game/ https://learn.ifs.name/d/turing1950/s/4-digital-computers/ https://learn.ifs.name/d/turing1950/s/5-universality-of-digital-computers/ https://learn.ifs.name/d/turing1950/s/6-contrary-views-on-the-main-question/ https://learn.ifs.name/d/turing1950/s/7-learning-machines/ https://learn.ifs.name/d/harris1954/ https://learn.ifs.name/d/harris1954/s/1-does-language-have-a-distributional-structure/ https://learn.ifs.name/d/harris1954/s/1-1-possibilities-of-structure-for-the-distributional-facts/ https://learn.ifs.name/d/harris1954/s/1-2-reality-of-the-structure/ https://learn.ifs.name/d/harris1954/s/2-distribution-and-meaning/ https://learn.ifs.name/d/harris1954/s/2-3-meaning-as-a-function-of-distribution/ https://learn.ifs.name/d/harris1954/s/3-distributional-analysis/ https://learn.ifs.name/d/harris1954/s/3-6-data/ https://learn.ifs.name/d/harris1954/s/4-distributional-relations/ https://learn.ifs.name/d/chomsky1956/ https://learn.ifs.name/d/chomsky1956/s/abstract/ https://learn.ifs.name/d/chomsky1956/s/1-introduction/ https://learn.ifs.name/d/chomsky1956/s/2-finite-state-markov-processes/ https://learn.ifs.name/d/chomsky1956/s/3-phrase-structure/ https://learn.ifs.name/d/chomsky1956/s/4-inadequacies-of-phrase-structure-grammar/ https://learn.ifs.name/d/chomsky1956/s/5-transformational-grammar/ https://learn.ifs.name/d/chomsky1956/s/6-explanatory-power-of-linguistic-theories/ https://learn.ifs.name/d/weizenbaum1966/ https://learn.ifs.name/d/weizenbaum1966/s/introduction/ https://learn.ifs.name/d/weizenbaum1966/s/the-eliza-program/ https://learn.ifs.name/d/weizenbaum1966/s/discussion/ https://learn.ifs.name/d/rabiner1989/ https://learn.ifs.name/d/rabiner1989/s/i-introduction/ https://learn.ifs.name/d/rabiner1989/s/ii-discrete-markov-processes/ https://learn.ifs.name/d/rabiner1989/s/ii-a-extension-to-hidden-markov-models/ https://learn.ifs.name/d/rabiner1989/s/ii-b-elements-of-an-hmm/ https://learn.ifs.name/d/rabiner1989/s/ii-c-the-three-basic-problems-for-hmms/ https://learn.ifs.name/d/rabiner1989/s/iii-a-solution-to-problem-1/ https://learn.ifs.name/d/rabiner1989/s/iii-b-solution-to-problem-2/ https://learn.ifs.name/d/rabiner1989/s/iii-c-solution-to-problem-3/ https://learn.ifs.name/d/rabiner1989/s/iv-types-of-hmms/ https://learn.ifs.name/d/rabiner1989/s/iv-a-continuous-observation-densities-in-hmms/ https://learn.ifs.name/d/rabiner1989/s/iv-c-variants-on-hmm-structures/ https://learn.ifs.name/d/rabiner1989/s/iv-d-explicit-state-duration-density/ https://learn.ifs.name/d/rabiner1989/s/iv-e-optimization-criterion/ https://learn.ifs.name/d/rabiner1989/s/v-implementation-issues-for-hmms/ https://learn.ifs.name/d/rabiner1989/s/vi-implementation-of-speech-recognizers-using-hmms/ https://learn.ifs.name/d/rabiner1989/s/viii-limitations-of-hmms/ https://learn.ifs.name/d/church1990/ https://learn.ifs.name/d/church1990/s/abstract/ https://learn.ifs.name/d/church1990/s/1-meaning-and-association/ https://learn.ifs.name/d/church1990/s/2-practical-applications/ https://learn.ifs.name/d/church1990/s/3-word-association-and-psycholinguistics/ https://learn.ifs.name/d/church1990/s/4-an-information-theoretic-measure/ https://learn.ifs.name/d/church1990/s/5-lexico-syntactic-regularities/ https://learn.ifs.name/d/church1990/s/6-preprocessing-with-a-part-of-speech-tagger/ https://learn.ifs.name/d/church1990/s/7-preprocessing-with-a-parser/ https://learn.ifs.name/d/church1990/s/8-applications-in-lexicography/ https://learn.ifs.name/d/church1990/s/9-conclusions/ https://learn.ifs.name/d/brown1993/ https://learn.ifs.name/d/brown1993/s/1-introduction/ https://learn.ifs.name/d/brown1993/s/2-statistical-translation/ https://learn.ifs.name/d/brown1993/s/3-alignments/ https://learn.ifs.name/d/brown1993/s/4-translation-models/ https://learn.ifs.name/d/brown1993/s/4-1-model-1/ https://learn.ifs.name/d/brown1993/s/4-2-model-2/ https://learn.ifs.name/d/brown1993/s/4-3-intermodel-interlude/ https://learn.ifs.name/d/brown1993/s/4-4-model-3/ https://learn.ifs.name/d/brown1993/s/4-5-deficiency/ https://learn.ifs.name/d/brown1993/s/4-6-model-4/ https://learn.ifs.name/d/brown1993/s/4-7-model-5/ https://learn.ifs.name/d/brown1993/s/5-results/ https://learn.ifs.name/d/brown1993/s/6-better-translation-models/ https://learn.ifs.name/d/marcus1993/ https://learn.ifs.name/d/marcus1993/s/1-introduction/ https://learn.ifs.name/d/marcus1993/s/2-1-a-simplified-pos-tagset-for-english/ https://learn.ifs.name/d/marcus1993/s/2-2-the-pos-tagset/ https://learn.ifs.name/d/marcus1993/s/2-3-the-pos-tagging-process/ https://learn.ifs.name/d/marcus1993/s/3-two-modes-of-annotation-an-experiment/ https://learn.ifs.name/d/marcus1993/s/4-1-bracketing-basic-methodology/ https://learn.ifs.name/d/marcus1993/s/4-2-the-syntactic-tagset/ https://learn.ifs.name/d/marcus1993/s/4-3-sample-bracketing-output/ https://learn.ifs.name/d/marcus1993/s/5-2-future-directions/ https://learn.ifs.name/d/miller1990/ https://learn.ifs.name/d/miller1990/s/introduction-to-wordnet/ https://learn.ifs.name/d/miller1990/s/nouns-in-wordnet-a-lexical-inheritance-system/ https://learn.ifs.name/d/miller1990/s/adjectives-in-wordnet/ https://learn.ifs.name/d/miller1990/s/english-verbs-as-a-semantic-net/ https://learn.ifs.name/d/miller1990/s/design-and-implementation-of-the-wordnet-lexical-database/ https://learn.ifs.name/d/yarowsky1995/ https://learn.ifs.name/d/yarowsky1995/s/1-introduction/ https://learn.ifs.name/d/yarowsky1995/s/2-one-sense-per-discourse/ https://learn.ifs.name/d/yarowsky1995/s/3-one-sense-per-collocation/ https://learn.ifs.name/d/yarowsky1995/s/4-the-algorithm/ https://learn.ifs.name/d/yarowsky1995/s/5-options-for-training-seeds/ https://learn.ifs.name/d/yarowsky1995/s/6-escaping-from-initial-misclassifications/ https://learn.ifs.name/d/yarowsky1995/s/7-using-the-one-sense-per-discourse-property/ https://learn.ifs.name/d/yarowsky1995/s/8-evaluation/ https://learn.ifs.name/d/yarowsky1995/s/9-comparison-with-previous-work/ https://learn.ifs.name/d/grosz1995/ https://learn.ifs.name/d/grosz1995/s/1-introduction/ https://learn.ifs.name/d/grosz1995/s/2-phenomena-to-be-explained/ https://learn.ifs.name/d/grosz1995/s/3-basic-center-definitions/ https://learn.ifs.name/d/grosz1995/s/4-claims-of-centering-theory/ https://learn.ifs.name/d/grosz1995/s/5-factors-governing-centering/ https://learn.ifs.name/d/grosz1995/s/6-constraints-on-center-movement-and-realization/ https://learn.ifs.name/d/grosz1995/s/7-applications-of-the-rules/ https://learn.ifs.name/d/grosz1995/s/8-requisite-properties-of-underlying-semantic-theory/ https://learn.ifs.name/d/grosz1995/s/9-comparison-with-previous-work/ https://learn.ifs.name/d/berger1996/ https://learn.ifs.name/d/berger1996/s/1-introduction/ https://learn.ifs.name/d/berger1996/s/2-a-maximum-entropy-overview/ https://learn.ifs.name/d/berger1996/s/3-2-statistics-features-and-constraints/ https://learn.ifs.name/d/berger1996/s/3-3-the-maximum-entropy-principle/ https://learn.ifs.name/d/berger1996/s/3-4-exponential-form/ https://learn.ifs.name/d/berger1996/s/3-5-relation-to-maximum-likelihood/ https://learn.ifs.name/d/berger1996/s/3-6-computing-the-parameters/ https://learn.ifs.name/d/berger1996/s/4-feature-selection/ https://learn.ifs.name/d/berger1996/s/5-1-review-of-statistical-translation/ https://learn.ifs.name/d/berger1996/s/5-2-context-dependent-word-models/ https://learn.ifs.name/d/berger1996/s/5-3-segmentation/ https://learn.ifs.name/d/berger1996/s/5-4-word-reordering/ https://learn.ifs.name/d/hochreiter1997/ https://learn.ifs.name/d/hochreiter1997/s/1-introduction/ https://learn.ifs.name/d/hochreiter1997/s/3-1-exponentially-decaying-error/ https://learn.ifs.name/d/hochreiter1997/s/3-2-constant-error-flow-naive-approach/ https://learn.ifs.name/d/hochreiter1997/s/4-1-memory-cells-and-gate-units/ https://learn.ifs.name/d/hochreiter1997/s/4-2-why-gate-units/ https://learn.ifs.name/d/hochreiter1997/s/4-4-memory-cell-blocks/ https://learn.ifs.name/d/hochreiter1997/s/4-5-learning/ https://learn.ifs.name/d/hochreiter1997/s/4-6-computational-complexity/ https://learn.ifs.name/d/hochreiter1997/s/4-7-abuse-problem-and-solutions/ https://learn.ifs.name/d/hochreiter1997/s/4-8-internal-state-drift-and-remedies/ https://learn.ifs.name/d/hochreiter1997/s/5-experiments/ https://learn.ifs.name/d/hochreiter1997/s/6-1-limitations-of-lstm/ https://learn.ifs.name/d/hochreiter1997/s/6-2-advantages-of-lstm/ https://learn.ifs.name/d/hochreiter1997/s/7-conclusion/ https://learn.ifs.name/d/lafferty2001/ https://learn.ifs.name/d/lafferty2001/s/1-introduction/ https://learn.ifs.name/d/lafferty2001/s/2-the-label-bias-problem/ https://learn.ifs.name/d/lafferty2001/s/3-conditional-random-fields/ https://learn.ifs.name/d/lafferty2001/s/4-parameter-estimation-for-crfs/ https://learn.ifs.name/d/lafferty2001/s/5-experiments/ https://learn.ifs.name/d/lafferty2001/s/6-further-aspects-of-crfs/ https://learn.ifs.name/d/lafferty2001/s/7-related-work-and-conclusions/ https://learn.ifs.name/d/papineni2002/ https://learn.ifs.name/d/papineni2002/s/1-introduction/ https://learn.ifs.name/d/papineni2002/s/2-1-modified-n-gram-precision/ https://learn.ifs.name/d/papineni2002/s/2-2-combining-the-modified-n-gram-precisions/ https://learn.ifs.name/d/papineni2002/s/2-2-1-the-trouble-with-recall/ https://learn.ifs.name/d/papineni2002/s/2-2-2-sentence-brevity-penalty/ https://learn.ifs.name/d/papineni2002/s/3-the-bleu-evaluation/ https://learn.ifs.name/d/papineni2002/s/4-the-human-evaluation/ https://learn.ifs.name/d/papineni2002/s/5-bleu-vs-the-human-evaluation/ https://learn.ifs.name/d/papineni2002/s/6-conclusion/ https://learn.ifs.name/d/pang2002/ https://learn.ifs.name/d/pang2002/s/1-introduction/ https://learn.ifs.name/d/pang2002/s/2-previous-work/ https://learn.ifs.name/d/pang2002/s/3-the-movie-review-domain/ https://learn.ifs.name/d/pang2002/s/4-a-closer-look-at-the-problem/ https://learn.ifs.name/d/pang2002/s/5-machine-learning-methods/ https://learn.ifs.name/d/pang2002/s/5-1-naive-bayes/ https://learn.ifs.name/d/pang2002/s/5-2-maximum-entropy/ https://learn.ifs.name/d/pang2002/s/5-3-support-vector-machines/ https://learn.ifs.name/d/pang2002/s/6-1-experimental-set-up/ https://learn.ifs.name/d/pang2002/s/6-2-results/ https://learn.ifs.name/d/pang2002/s/7-discussion/ https://learn.ifs.name/d/collins2002/ https://learn.ifs.name/d/collins2002/s/1-introduction/ https://learn.ifs.name/d/collins2002/s/2-1-hmm-taggers/ https://learn.ifs.name/d/collins2002/s/2-2-local-and-global-feature-vectors/ https://learn.ifs.name/d/collins2002/s/2-3-maximum-entropy-taggers/ https://learn.ifs.name/d/collins2002/s/2-4-a-new-estimation-method/ https://learn.ifs.name/d/collins2002/s/2-5-averaging-parameters/ https://learn.ifs.name/d/collins2002/s/3-theory-justifying-the-algorithm/ https://learn.ifs.name/d/collins2002/s/3-1-theory-for-inseparable-data/ https://learn.ifs.name/d/collins2002/s/3-2-generalization-results/ https://learn.ifs.name/d/collins2002/s/4-experiments/ https://learn.ifs.name/d/collins2002/s/6-conclusions/ https://learn.ifs.name/d/koehn2003/ https://learn.ifs.name/d/koehn2003/s/1-introduction/ https://learn.ifs.name/d/koehn2003/s/2-1-model/ https://learn.ifs.name/d/koehn2003/s/2-2-decoder/ https://learn.ifs.name/d/koehn2003/s/3-methods-for-learning-phrase-translation/ https://learn.ifs.name/d/koehn2003/s/3-1-phrases-from-word-based-alignments/ https://learn.ifs.name/d/koehn2003/s/3-2-syntactic-phrases/ https://learn.ifs.name/d/koehn2003/s/3-3-phrases-from-phrase-alignments/ https://learn.ifs.name/d/koehn2003/s/4-1-comparison-of-core-methods/ https://learn.ifs.name/d/koehn2003/s/4-2-weighting-syntactic-phrases/ https://learn.ifs.name/d/koehn2003/s/4-3-maximum-phrase-length/ https://learn.ifs.name/d/koehn2003/s/4-4-lexical-weighting/ https://learn.ifs.name/d/koehn2003/s/4-5-phrase-extraction-heuristic/ https://learn.ifs.name/d/koehn2003/s/4-6-simpler-underlying-word-based-models/ https://learn.ifs.name/d/koehn2003/s/4-7-other-language-pairs/ https://learn.ifs.name/d/koehn2003/s/5-conclusion/ https://learn.ifs.name/d/klein2003/ https://learn.ifs.name/d/klein2003/s/introduction/ https://learn.ifs.name/d/klein2003/s/1-experimental-setup/ https://learn.ifs.name/d/klein2003/s/2-vertical-and-horizontal-markovization/ https://learn.ifs.name/d/klein2003/s/3-external-vs-internal-annotation/ https://learn.ifs.name/d/klein2003/s/4-tag-splitting/ https://learn.ifs.name/d/klein2003/s/5-what-is-an-unlexicalized-grammar/ https://learn.ifs.name/d/klein2003/s/6-annotations-already-in-the-treebank/ https://learn.ifs.name/d/klein2003/s/7-head-annotation/ https://learn.ifs.name/d/klein2003/s/8-distance/ https://learn.ifs.name/d/klein2003/s/9-final-results/ https://learn.ifs.name/d/klein2003/s/10-conclusion/ https://learn.ifs.name/d/bengio2003/ https://learn.ifs.name/d/bengio2003/s/1-introduction/ https://learn.ifs.name/d/bengio2003/s/1-1-fighting-the-curse-of-dimensionality-with-distributed-representations/ https://learn.ifs.name/d/bengio2003/s/1-2-relation-to-previous-work/ https://learn.ifs.name/d/bengio2003/s/2-a-neural-model/ https://learn.ifs.name/d/bengio2003/s/3-parallel-implementation/ https://learn.ifs.name/d/bengio2003/s/3-2-parameter-parallel-processing/ https://learn.ifs.name/d/bengio2003/s/4-experimental-results/ https://learn.ifs.name/d/bengio2003/s/4-1-n-gram-models/ https://learn.ifs.name/d/bengio2003/s/4-2-results/ https://learn.ifs.name/d/bengio2003/s/5-1-an-energy-minimization-network/ https://learn.ifs.name/d/bengio2003/s/5-2-other-future-work/ https://learn.ifs.name/d/bengio2003/s/6-conclusion/ https://learn.ifs.name/d/blei2003/ https://learn.ifs.name/d/blei2003/s/1-introduction/ https://learn.ifs.name/d/blei2003/s/3-latent-dirichlet-allocation/ https://learn.ifs.name/d/blei2003/s/3-2-a-continuous-mixture-of-unigrams/ https://learn.ifs.name/d/blei2003/s/4-2-mixture-of-unigrams/ https://learn.ifs.name/d/blei2003/s/4-3-probabilistic-latent-semantic-indexing/ https://learn.ifs.name/d/blei2003/s/4-4-a-geometric-interpretation/ https://learn.ifs.name/d/blei2003/s/5-1-inference/ https://learn.ifs.name/d/blei2003/s/5-2-variational-inference/ https://learn.ifs.name/d/blei2003/s/5-3-parameter-estimation/ https://learn.ifs.name/d/blei2003/s/5-4-smoothing/ https://learn.ifs.name/d/blei2003/s/6-example/ https://learn.ifs.name/d/blei2003/s/7-1-document-modeling/ https://learn.ifs.name/d/blei2003/s/7-2-document-classification/ https://learn.ifs.name/d/blei2003/s/7-3-collaborative-filtering/ https://learn.ifs.name/d/blei2003/s/8-discussion/ https://learn.ifs.name/d/mcdonald2005/ https://learn.ifs.name/d/mcdonald2005/s/1-introduction/ https://learn.ifs.name/d/mcdonald2005/s/2-1-edge-based-factorization/ https://learn.ifs.name/d/mcdonald2005/s/2-2-maximum-spanning-trees/ https://learn.ifs.name/d/mcdonald2005/s/2-2-1-non-projective-trees/ https://learn.ifs.name/d/mcdonald2005/s/2-2-2-projective-trees/ https://learn.ifs.name/d/mcdonald2005/s/2-3-dependency-trees-as-msts-summary/ https://learn.ifs.name/d/mcdonald2005/s/3-online-large-margin-learning/ https://learn.ifs.name/d/mcdonald2005/s/3-1-single-best-mira/ https://learn.ifs.name/d/mcdonald2005/s/3-2-factored-mira/ https://learn.ifs.name/d/mcdonald2005/s/4-experiments/ https://learn.ifs.name/d/mcdonald2005/s/4-1-results/ https://learn.ifs.name/d/mcdonald2005/s/5-discussion/ https://learn.ifs.name/d/graves2006/ https://learn.ifs.name/d/graves2006/s/1-introduction/ https://learn.ifs.name/d/graves2006/s/2-temporal-classification/ https://learn.ifs.name/d/graves2006/s/2-1-label-error-rate/ https://learn.ifs.name/d/graves2006/s/3-1-from-network-outputs-to-labellings/ https://learn.ifs.name/d/graves2006/s/3-2-constructing-the-classifier/ https://learn.ifs.name/d/graves2006/s/4-training-the-network/ https://learn.ifs.name/d/graves2006/s/4-1-the-ctc-forward-backward-algorithm/ https://learn.ifs.name/d/graves2006/s/4-2-maximum-likelihood-training/ https://learn.ifs.name/d/graves2006/s/5-experiments/ https://learn.ifs.name/d/graves2006/s/5-1-data/ https://learn.ifs.name/d/graves2006/s/5-2-experimental-setup/ https://learn.ifs.name/d/graves2006/s/5-3-experimental-results/ https://learn.ifs.name/d/graves2006/s/6-discussion-and-future-work/ https://learn.ifs.name/d/nivre2008/ https://learn.ifs.name/d/nivre2008/s/1-introduction/ https://learn.ifs.name/d/nivre2008/s/2-dependency-parsing/ https://learn.ifs.name/d/nivre2008/s/3-deterministic-incremental-dependency-parsing/ https://learn.ifs.name/d/nivre2008/s/4-stack-based-algorithms/ https://learn.ifs.name/d/nivre2008/s/4-1-arc-standard-parsing/ https://learn.ifs.name/d/nivre2008/s/4-2-arc-eager-parsing/ https://learn.ifs.name/d/nivre2008/s/5-list-based-algorithms/ https://learn.ifs.name/d/nivre2008/s/5-1-non-projective-parsing/ https://learn.ifs.name/d/nivre2008/s/5-2-projective-parsing/ https://learn.ifs.name/d/nivre2008/s/6-1-experimental-setup/ https://learn.ifs.name/d/nivre2008/s/6-2-parsing-accuracy/ https://learn.ifs.name/d/nivre2008/s/6-3-efficiency/ https://learn.ifs.name/d/nivre2008/s/8-conclusion/ https://learn.ifs.name/d/collobert2011/ https://learn.ifs.name/d/collobert2011/s/1-introduction/ https://learn.ifs.name/d/collobert2011/s/2-the-benchmark-tasks/ https://learn.ifs.name/d/collobert2011/s/3-the-networks/ https://learn.ifs.name/d/collobert2011/s/3-2-transforming-words-into-feature-vectors/ https://learn.ifs.name/d/collobert2011/s/3-3-1-window-approach/ https://learn.ifs.name/d/collobert2011/s/3-3-2-sentence-approach/ https://learn.ifs.name/d/collobert2011/s/3-3-3-tagging-schemes/ https://learn.ifs.name/d/collobert2011/s/3-4-1-word-level-log-likelihood/ https://learn.ifs.name/d/collobert2011/s/3-4-2-sentence-level-log-likelihood/ https://learn.ifs.name/d/collobert2011/s/3-5-supervised-benchmark-results/ https://learn.ifs.name/d/collobert2011/s/4-2-ranking-criterion-versus-entropy-criterion/ https://learn.ifs.name/d/collobert2011/s/4-3-training-language-models/ https://learn.ifs.name/d/collobert2011/s/4-4-embeddings/ https://learn.ifs.name/d/collobert2011/s/4-5-semi-supervised-benchmark-results/ https://learn.ifs.name/d/collobert2011/s/4-6-ranking-and-language/ https://learn.ifs.name/d/collobert2011/s/5-multi-task-learning/ https://learn.ifs.name/d/collobert2011/s/6-the-temptation/ https://learn.ifs.name/d/collobert2011/s/6-5-parsing/ https://learn.ifs.name/d/collobert2011/s/6-6-word-representations/ https://learn.ifs.name/d/collobert2011/s/6-7-engineering-a-sweet-spot/ https://learn.ifs.name/d/collobert2011/s/7-critical-discussion/ https://learn.ifs.name/d/mikolov2013/ https://learn.ifs.name/d/mikolov2013/s/1-introduction/ https://learn.ifs.name/d/mikolov2013/s/2-the-skip-gram-model/ https://learn.ifs.name/d/mikolov2013/s/2-1-hierarchical-softmax/ https://learn.ifs.name/d/mikolov2013/s/2-2-negative-sampling/ https://learn.ifs.name/d/mikolov2013/s/2-3-subsampling-of-frequent-words/ https://learn.ifs.name/d/mikolov2013/s/3-empirical-results/ https://learn.ifs.name/d/mikolov2013/s/4-learning-phrases/ https://learn.ifs.name/d/mikolov2013/s/4-1-phrase-skip-gram-results/ https://learn.ifs.name/d/mikolov2013/s/5-additive-compositionality/ https://learn.ifs.name/d/mikolov2013/s/6-comparison-to-published-word-representations/ https://learn.ifs.name/d/mikolov2013/s/7-conclusion/ https://learn.ifs.name/d/pennington2014/ https://learn.ifs.name/d/pennington2014/s/1-introduction/ https://learn.ifs.name/d/pennington2014/s/2-related-work/ https://learn.ifs.name/d/pennington2014/s/3-the-glove-model/ https://learn.ifs.name/d/pennington2014/s/3-1-relationship-to-other-models/ https://learn.ifs.name/d/pennington2014/s/3-2-complexity-of-the-model/ https://learn.ifs.name/d/pennington2014/s/4-1-evaluation-methods/ https://learn.ifs.name/d/pennington2014/s/4-2-corpora-and-training-details/ https://learn.ifs.name/d/pennington2014/s/4-3-results/ https://learn.ifs.name/d/pennington2014/s/4-5-model-analysis-vector-length-and-context-size/ https://learn.ifs.name/d/pennington2014/s/4-6-model-analysis-corpus-size/ https://learn.ifs.name/d/pennington2014/s/4-7-model-analysis-comparison-with-word2vec/ https://learn.ifs.name/d/pennington2014/s/5-conclusion/ https://learn.ifs.name/d/sutskever2014/ https://learn.ifs.name/d/sutskever2014/s/1-introduction/ https://learn.ifs.name/d/sutskever2014/s/2-the-model/ https://learn.ifs.name/d/sutskever2014/s/3-1-dataset-details/ https://learn.ifs.name/d/sutskever2014/s/3-2-decoding-and-rescoring/ https://learn.ifs.name/d/sutskever2014/s/3-3-reversing-the-source-sentences/ https://learn.ifs.name/d/sutskever2014/s/3-4-training-details/ https://learn.ifs.name/d/sutskever2014/s/3-5-parallelization/ https://learn.ifs.name/d/sutskever2014/s/3-6-experimental-results/ https://learn.ifs.name/d/sutskever2014/s/3-7-performance-on-long-sentences/ https://learn.ifs.name/d/sutskever2014/s/3-8-model-analysis/ https://learn.ifs.name/d/sutskever2014/s/5-conclusion/ https://learn.ifs.name/d/bahdanau2015/ https://learn.ifs.name/d/bahdanau2015/s/1-introduction/ https://learn.ifs.name/d/bahdanau2015/s/2-1-rnn-encoder–decoder/ https://learn.ifs.name/d/bahdanau2015/s/3-1-decoder-general-description/ https://learn.ifs.name/d/bahdanau2015/s/3-2-encoder-bidirectional-rnn-for-annotating-sequences/ https://learn.ifs.name/d/bahdanau2015/s/4-experiment-settings/ https://learn.ifs.name/d/bahdanau2015/s/5-1-quantitative-results/ https://learn.ifs.name/d/bahdanau2015/s/5-2-1-alignment/ https://learn.ifs.name/d/bahdanau2015/s/5-2-2-long-sentences/ https://learn.ifs.name/d/bahdanau2015/s/6-1-learning-to-align/ https://learn.ifs.name/d/bahdanau2015/s/7-conclusion/ https://learn.ifs.name/d/bowman2015/ https://learn.ifs.name/d/bowman2015/s/1-introduction/ https://learn.ifs.name/d/bowman2015/s/2-a-new-corpus-for-nli/ https://learn.ifs.name/d/bowman2015/s/2-1-data-collection/ https://learn.ifs.name/d/bowman2015/s/2-2-data-validation/ https://learn.ifs.name/d/bowman2015/s/2-3-the-distributed-corpus/ https://learn.ifs.name/d/bowman2015/s/3-1-excitement-open-platform-models/ https://learn.ifs.name/d/bowman2015/s/3-2-lexicalized-classifier/ https://learn.ifs.name/d/bowman2015/s/3-3-sentence-embeddings-and-nli/ https://learn.ifs.name/d/bowman2015/s/3-4-analysis-and-discussion/ https://learn.ifs.name/d/bowman2015/s/4-transfer-learning-with-sick/ https://learn.ifs.name/d/bowman2015/s/5-conclusion/ https://learn.ifs.name/d/sennrich2016/ https://learn.ifs.name/d/sennrich2016/s/1-introduction/ https://learn.ifs.name/d/sennrich2016/s/3-subword-translation/ https://learn.ifs.name/d/sennrich2016/s/3-1-related-work/ https://learn.ifs.name/d/sennrich2016/s/3-2-byte-pair-encoding-bpe/ https://learn.ifs.name/d/sennrich2016/s/4-evaluation/ https://learn.ifs.name/d/sennrich2016/s/4-1-subword-statistics/ https://learn.ifs.name/d/sennrich2016/s/4-2-translation-experiments/ https://learn.ifs.name/d/sennrich2016/s/5-1-unigram-accuracy/ https://learn.ifs.name/d/sennrich2016/s/5-2-manual-analysis/ https://learn.ifs.name/d/rajpurkar2016/ https://learn.ifs.name/d/rajpurkar2016/s/1-introduction/ https://learn.ifs.name/d/rajpurkar2016/s/2-existing-datasets/ https://learn.ifs.name/d/rajpurkar2016/s/3-dataset-collection/ https://learn.ifs.name/d/rajpurkar2016/s/4-dataset-analysis/ https://learn.ifs.name/d/rajpurkar2016/s/5-methods/ https://learn.ifs.name/d/rajpurkar2016/s/5-2-logistic-regression/ https://learn.ifs.name/d/rajpurkar2016/s/6-1-model-evaluation/ https://learn.ifs.name/d/rajpurkar2016/s/6-2-human-performance/ https://learn.ifs.name/d/rajpurkar2016/s/6-3-model-performance/ https://learn.ifs.name/d/rajpurkar2016/s/7-conclusion/ https://learn.ifs.name/d/vaswani2017/ https://learn.ifs.name/d/vaswani2017/s/1-introduction/ https://learn.ifs.name/d/vaswani2017/s/2-background/ https://learn.ifs.name/d/vaswani2017/s/3-1-encoder-and-decoder-stacks/ https://learn.ifs.name/d/vaswani2017/s/3-2-attention/ https://learn.ifs.name/d/vaswani2017/s/3-2-1-scaled-dot-product-attention/ https://learn.ifs.name/d/vaswani2017/s/3-2-2-multi-head-attention/ https://learn.ifs.name/d/vaswani2017/s/3-2-3-applications-of-attention-in-our-model/ https://learn.ifs.name/d/vaswani2017/s/3-3-position-wise-feed-forward-networks/ https://learn.ifs.name/d/vaswani2017/s/3-4-embeddings-and-softmax/ https://learn.ifs.name/d/vaswani2017/s/3-5-positional-encoding/ https://learn.ifs.name/d/vaswani2017/s/4-why-self-attention/ https://learn.ifs.name/d/vaswani2017/s/5-1-training-data-and-batching/ https://learn.ifs.name/d/vaswani2017/s/5-3-optimizer/ https://learn.ifs.name/d/vaswani2017/s/5-4-regularization/ https://learn.ifs.name/d/vaswani2017/s/6-1-machine-translation/ https://learn.ifs.name/d/vaswani2017/s/6-2-model-variations/ https://learn.ifs.name/d/vaswani2017/s/7-conclusion/ https://learn.ifs.name/d/peters2018/ https://learn.ifs.name/d/peters2018/s/1-introduction/ https://learn.ifs.name/d/peters2018/s/2-related-work/ https://learn.ifs.name/d/peters2018/s/3-1-bidirectional-language-models/ https://learn.ifs.name/d/peters2018/s/3-2-elmo/ https://learn.ifs.name/d/peters2018/s/3-3-using-bilms-for-supervised-nlp-tasks/ https://learn.ifs.name/d/peters2018/s/3-4-pre-trained-bidirectional-language-model-architecture/ https://learn.ifs.name/d/peters2018/s/4-evaluation/ https://learn.ifs.name/d/peters2018/s/5-1-alternate-layer-weighting-schemes/ https://learn.ifs.name/d/peters2018/s/5-2-where-to-include-elmo/ https://learn.ifs.name/d/peters2018/s/5-3-what-information-is-captured-by-the-bilm’s-representations/ https://learn.ifs.name/d/peters2018/s/5-4-sample-efficiency/ https://learn.ifs.name/d/peters2018/s/5-5-visualization-of-learned-weights/ https://learn.ifs.name/d/peters2018/s/5-6-contextual-vs-sub-word-information/ https://learn.ifs.name/d/gururangan2018/ https://learn.ifs.name/d/gururangan2018/s/1-introduction/ https://learn.ifs.name/d/gururangan2018/s/2-annotation-artifacts-are-common/ https://learn.ifs.name/d/gururangan2018/s/3-1-lexical-choice/ https://learn.ifs.name/d/gururangan2018/s/3-2-sentence-length/ https://learn.ifs.name/d/gururangan2018/s/4-re-evaluating-nli-models/ https://learn.ifs.name/d/gururangan2018/s/5-discussion/ https://learn.ifs.name/d/wang2019/ https://learn.ifs.name/d/wang2019/s/1-introduction/ https://learn.ifs.name/d/wang2019/s/2-related-work/ https://learn.ifs.name/d/wang2019/s/3-tasks/ https://learn.ifs.name/d/wang2019/s/3-1-single-sentence-tasks/ https://learn.ifs.name/d/wang2019/s/3-2-similarity-and-paraphrase-tasks/ https://learn.ifs.name/d/wang2019/s/3-3-inference-tasks/ https://learn.ifs.name/d/wang2019/s/3-4-evaluation/ https://learn.ifs.name/d/wang2019/s/4-diagnostic-dataset/ https://learn.ifs.name/d/wang2019/s/5-baselines/ https://learn.ifs.name/d/wang2019/s/6-benchmark-results/ https://learn.ifs.name/d/wang2019/s/7-analysis/ https://learn.ifs.name/d/wang2019/s/8-conclusion/ https://learn.ifs.name/d/devlin2019/ https://learn.ifs.name/d/devlin2019/s/1-introduction/ https://learn.ifs.name/d/devlin2019/s/3-bert/ https://learn.ifs.name/d/devlin2019/s/3-1-pre-training-bert/ https://learn.ifs.name/d/devlin2019/s/3-2-fine-tuning-bert/ https://learn.ifs.name/d/devlin2019/s/4-1-glue/ https://learn.ifs.name/d/devlin2019/s/4-2-squad-v1-1/ https://learn.ifs.name/d/devlin2019/s/4-3-squad-v2-0/ https://learn.ifs.name/d/devlin2019/s/4-4-swag/ https://learn.ifs.name/d/devlin2019/s/5-1-effect-of-pre-training-tasks/ https://learn.ifs.name/d/devlin2019/s/5-2-effect-of-model-size/ https://learn.ifs.name/d/devlin2019/s/5-3-feature-based-approach-with-bert/ https://learn.ifs.name/d/radford2019/ https://learn.ifs.name/d/radford2019/s/1-introduction/ https://learn.ifs.name/d/radford2019/s/2-approach/ https://learn.ifs.name/d/radford2019/s/2-1-training-dataset/ https://learn.ifs.name/d/radford2019/s/2-2-input-representation/ https://learn.ifs.name/d/radford2019/s/2-3-model/ https://learn.ifs.name/d/radford2019/s/3-1-language-modeling/ https://learn.ifs.name/d/radford2019/s/3-3-lambada/ https://learn.ifs.name/d/radford2019/s/3-5-reading-comprehension/ https://learn.ifs.name/d/radford2019/s/3-6-summarization/ https://learn.ifs.name/d/radford2019/s/3-7-translation/ https://learn.ifs.name/d/radford2019/s/3-8-question-answering/ https://learn.ifs.name/d/radford2019/s/4-generalization-vs-memorization/ https://learn.ifs.name/d/radford2019/s/6-discussion/ https://learn.ifs.name/d/tenney2019/ https://learn.ifs.name/d/tenney2019/s/1-introduction/ https://learn.ifs.name/d/tenney2019/s/2-model/ https://learn.ifs.name/d/tenney2019/s/3-1-scalar-mixing-weights/ https://learn.ifs.name/d/tenney2019/s/3-2-cumulative-scoring/ https://learn.ifs.name/d/tenney2019/s/4-results/ https://learn.ifs.name/d/tenney2019/s/4-1-per-example-analysis/ https://learn.ifs.name/d/tenney2019/s/5-conclusion/ https://learn.ifs.name/d/hewitt2019/ https://learn.ifs.name/d/hewitt2019/s/1-introduction/ https://learn.ifs.name/d/hewitt2019/s/2-methods/ https://learn.ifs.name/d/hewitt2019/s/2-1-the-structural-probe/ https://learn.ifs.name/d/hewitt2019/s/2-2-properties-of-the-structural-probe/ https://learn.ifs.name/d/hewitt2019/s/2-3-tree-depth-structural-probes/ https://learn.ifs.name/d/hewitt2019/s/3-experiments/ https://learn.ifs.name/d/hewitt2019/s/3-1-tree-distance-evaluation-metrics/ https://learn.ifs.name/d/hewitt2019/s/3-2-tree-depth-evaluation-metrics/ https://learn.ifs.name/d/hewitt2019/s/4-results/ https://learn.ifs.name/d/hewitt2019/s/4-1-analysis-of-linear-transformation-rank/ https://learn.ifs.name/d/hewitt2019/s/5-discussion-and-conclusion/ https://learn.ifs.name/d/raffel2020/ https://learn.ifs.name/d/raffel2020/s/1-introduction/ https://learn.ifs.name/d/raffel2020/s/2-1-model/ https://learn.ifs.name/d/raffel2020/s/2-2-the-colossal-clean-crawled-corpus/ https://learn.ifs.name/d/raffel2020/s/2-4-input-and-output-format/ https://learn.ifs.name/d/raffel2020/s/3-experiments/ https://learn.ifs.name/d/raffel2020/s/3-1-baseline/ https://learn.ifs.name/d/raffel2020/s/3-2-architectures/ https://learn.ifs.name/d/raffel2020/s/3-3-unsupervised-objectives/ https://learn.ifs.name/d/raffel2020/s/3-4-pre-training-data-set/ https://learn.ifs.name/d/raffel2020/s/3-5-training-strategy/ https://learn.ifs.name/d/raffel2020/s/3-6-scaling/ https://learn.ifs.name/d/raffel2020/s/3-7-putting-it-all-together/ https://learn.ifs.name/d/raffel2020/s/4-2-outlook/ https://learn.ifs.name/d/kaplan2020/ https://learn.ifs.name/d/kaplan2020/s/1-1-summary/ https://learn.ifs.name/d/kaplan2020/s/1-2-summary-of-scaling-laws/ https://learn.ifs.name/d/kaplan2020/s/1-3-notation/ https://learn.ifs.name/d/kaplan2020/s/2-background-and-methods/ https://learn.ifs.name/d/kaplan2020/s/3-2-1-comparing-to-lstms-and-universal-transformers/ https://learn.ifs.name/d/kaplan2020/s/4-charting-the-infinite-data-limit-and-overfitting/ https://learn.ifs.name/d/kaplan2020/s/5-1-adjustment-for-training-at-b-crit-l/ https://learn.ifs.name/d/kaplan2020/s/5-2-results-for-l-n-s-min-and-performance-with-model-size-and-compute/ https://learn.ifs.name/d/kaplan2020/s/6-3-contradictions-and-a-conjecture/ https://learn.ifs.name/d/kaplan2020/s/8-discussion/ https://learn.ifs.name/d/brown2020/ https://learn.ifs.name/d/brown2020/s/1-introduction/ https://learn.ifs.name/d/brown2020/s/2-approach/ https://learn.ifs.name/d/brown2020/s/2-1-model-and-architectures/ https://learn.ifs.name/d/brown2020/s/2-2-training-dataset/ https://learn.ifs.name/d/brown2020/s/2-4-evaluation/ https://learn.ifs.name/d/brown2020/s/3-1-language-modeling-cloze-and-completion-tasks/ https://learn.ifs.name/d/brown2020/s/3-2-question-answering/ https://learn.ifs.name/d/brown2020/s/3-3-translation/ https://learn.ifs.name/d/brown2020/s/3-4-superglue/ https://learn.ifs.name/d/brown2020/s/4-measuring-and-preventing-memorization-of-benchmarks/ https://learn.ifs.name/d/brown2020/s/5-limitations/ https://learn.ifs.name/d/brown2020/s/7-1-misuse-of-language-models/ https://learn.ifs.name/d/brown2020/s/7-2-fairness-bias-and-representation/ https://learn.ifs.name/d/brown2020/s/7-4-news-generation/ https://learn.ifs.name/d/lewis2020/ https://learn.ifs.name/d/lewis2020/s/1-introduction/ https://learn.ifs.name/d/lewis2020/s/2-1-models/ https://learn.ifs.name/d/lewis2020/s/2-2-retriever-dpr/ https://learn.ifs.name/d/lewis2020/s/2-3-generator-bart/ https://learn.ifs.name/d/lewis2020/s/2-4-training/ https://learn.ifs.name/d/lewis2020/s/2-5-decoding/ https://learn.ifs.name/d/lewis2020/s/3-experiments/ https://learn.ifs.name/d/lewis2020/s/4-1-open-domain-question-answering/ https://learn.ifs.name/d/lewis2020/s/4-2-abstractive-question-answering/ https://learn.ifs.name/d/lewis2020/s/4-3-jeopardy-question-generation/ https://learn.ifs.name/d/lewis2020/s/4-4-fact-verification/ https://learn.ifs.name/d/lewis2020/s/4-5-additional-results/ https://learn.ifs.name/d/lewis2020/s/6-discussion/ https://learn.ifs.name/d/bender2020/ https://learn.ifs.name/d/bender2020/s/1-introduction/ https://learn.ifs.name/d/bender2020/s/2-large-lms-hype-and-analysis/ https://learn.ifs.name/d/bender2020/s/3-what-is-meaning/ https://learn.ifs.name/d/bender2020/s/3-2-meaning-and-intelligence/ https://learn.ifs.name/d/bender2020/s/4-the-octopus-test/ https://learn.ifs.name/d/bender2020/s/5-more-constrained-thought-experiments/ https://learn.ifs.name/d/bender2020/s/6-human-language-acquisition/ https://learn.ifs.name/d/bender2020/s/7-distributional-semantics/ https://learn.ifs.name/d/bender2020/s/8-on-climbing-the-right-hills/ https://learn.ifs.name/d/bender2020/s/9-some-possible-counterarguments/ https://learn.ifs.name/d/baevski2020/ https://learn.ifs.name/d/baevski2020/s/1-introduction/ https://learn.ifs.name/d/baevski2020/s/2-model/ https://learn.ifs.name/d/baevski2020/s/3-1-masking/ https://learn.ifs.name/d/baevski2020/s/3-2-objective/ https://learn.ifs.name/d/baevski2020/s/3-3-fine-tuning/ https://learn.ifs.name/d/baevski2020/s/4-1-datasets/ https://learn.ifs.name/d/baevski2020/s/4-2-pre-training/ https://learn.ifs.name/d/baevski2020/s/5-1-low-resource-labeled-data-evaluation/ https://learn.ifs.name/d/baevski2020/s/5-2-high-resource-labeled-data-evaluation-on-librispeech/ https://learn.ifs.name/d/baevski2020/s/5-3-phoneme-recognition-on-timit/ https://learn.ifs.name/d/baevski2020/s/5-4-ablations/ https://learn.ifs.name/d/baevski2020/s/6-conclusion/ https://learn.ifs.name/d/bender2021/ https://learn.ifs.name/d/bender2021/s/1-introduction/ https://learn.ifs.name/d/bender2021/s/2-background/ https://learn.ifs.name/d/bender2021/s/3-environmental-and-financial-cost/ https://learn.ifs.name/d/bender2021/s/4-1-size-doesn’t-guarantee-diversity/ https://learn.ifs.name/d/bender2021/s/4-2-static-data-changing-social-views/ https://learn.ifs.name/d/bender2021/s/4-3-encoding-bias/ https://learn.ifs.name/d/bender2021/s/4-4-curation-documentation-and-accountability/ https://learn.ifs.name/d/bender2021/s/5-down-the-garden-path/ https://learn.ifs.name/d/bender2021/s/6-1-coherence-in-the-eye-of-the-beholder/ https://learn.ifs.name/d/bender2021/s/6-2-risks-and-harms/ https://learn.ifs.name/d/bender2021/s/6-3-summary/ https://learn.ifs.name/d/bender2021/s/7-paths-forward/ https://learn.ifs.name/d/bender2021/s/8-conclusion/ https://learn.ifs.name/d/hoffmann2022/ https://learn.ifs.name/d/hoffmann2022/s/1-introduction/ https://learn.ifs.name/d/hoffmann2022/s/2-related-work/ https://learn.ifs.name/d/hoffmann2022/s/3-estimating-the-optimal-parameter-training-tokens-allocation/ https://learn.ifs.name/d/hoffmann2022/s/3-1-approach-1-fix-model-sizes-and-vary-number-of-training-tokens/ https://learn.ifs.name/d/hoffmann2022/s/3-2-approach-2-isoflop-profiles/ https://learn.ifs.name/d/hoffmann2022/s/3-3-approach-3-fitting-a-parametric-loss-function/ https://learn.ifs.name/d/hoffmann2022/s/3-4-optimal-model-scaling/ https://learn.ifs.name/d/hoffmann2022/s/4-chinchilla/ https://learn.ifs.name/d/hoffmann2022/s/4-1-model-and-training-details/ https://learn.ifs.name/d/hoffmann2022/s/4-2-results/ https://learn.ifs.name/d/hoffmann2022/s/5-discussion-and-conclusion/ https://learn.ifs.name/d/wei2022/ https://learn.ifs.name/d/wei2022/s/1-introduction/ https://learn.ifs.name/d/wei2022/s/2-chain-of-thought-prompting/ https://learn.ifs.name/d/wei2022/s/3-1-experimental-setup/ https://learn.ifs.name/d/wei2022/s/3-2-results/ https://learn.ifs.name/d/wei2022/s/3-3-ablation-study/ https://learn.ifs.name/d/wei2022/s/3-4-robustness-of-chain-of-thought/ https://learn.ifs.name/d/wei2022/s/4-commonsense-reasoning/ https://learn.ifs.name/d/wei2022/s/5-symbolic-reasoning/ https://learn.ifs.name/d/wei2022/s/6-discussion/ https://learn.ifs.name/d/wei2022/s/7-related-work/ https://learn.ifs.name/d/ouyang2022/ https://learn.ifs.name/d/ouyang2022/s/1-introduction/ https://learn.ifs.name/d/ouyang2022/s/3-1-high-level-methodology/ https://learn.ifs.name/d/ouyang2022/s/3-2-dataset/ https://learn.ifs.name/d/ouyang2022/s/3-3-human-data-collection/ https://learn.ifs.name/d/ouyang2022/s/3-4-models/ https://learn.ifs.name/d/ouyang2022/s/3-5-evaluation/ https://learn.ifs.name/d/ouyang2022/s/4-1-results-on-the-api-distribution/ https://learn.ifs.name/d/ouyang2022/s/4-2-results-on-public-nlp-datasets/ https://learn.ifs.name/d/ouyang2022/s/4-3-qualitative-results/ https://learn.ifs.name/d/ouyang2022/s/5-1-implications-for-alignment-research/ https://learn.ifs.name/d/ouyang2022/s/5-2-limitations/ https://learn.ifs.name/d/hu2022/ https://learn.ifs.name/d/hu2022/s/1-introduction/ https://learn.ifs.name/d/hu2022/s/2-problem-statement/ https://learn.ifs.name/d/hu2022/s/3-aren’t-existing-solutions-good-enough/ https://learn.ifs.name/d/hu2022/s/4-1-low-rank-parametrized-update-matrices/ https://learn.ifs.name/d/hu2022/s/4-2-applying-lora-to-transformer/ https://learn.ifs.name/d/hu2022/s/5-empirical-experiments/ https://learn.ifs.name/d/hu2022/s/5-5-scaling-up-to-gpt-3-175b/ https://learn.ifs.name/d/hu2022/s/7-1-which-weight-matrices-in-transformer-should-we-apply-lora-to/ https://learn.ifs.name/d/hu2022/s/7-2-what-is-the-optimal-rank-r-for-lora/ https://learn.ifs.name/d/hu2022/s/7-3-how-does-the-adaptation-matrix-δw-compare-to-w/ https://learn.ifs.name/d/leviathan2023/ https://learn.ifs.name/d/leviathan2023/s/1-introduction/ https://learn.ifs.name/d/leviathan2023/s/2-1-overview/ https://learn.ifs.name/d/leviathan2023/s/2-2-standardized-sampling/ https://learn.ifs.name/d/leviathan2023/s/2-3-speculative-sampling/ https://learn.ifs.name/d/leviathan2023/s/3-1-number-of-generated-tokens/ https://learn.ifs.name/d/leviathan2023/s/3-3-walltime-improvement/ https://learn.ifs.name/d/leviathan2023/s/3-4-number-of-arithmetic-operations/ https://learn.ifs.name/d/leviathan2023/s/3-5-choosing-γ/ https://learn.ifs.name/d/leviathan2023/s/3-6-approximation-models/ https://learn.ifs.name/d/leviathan2023/s/4-1-empirical-walltime-improvement/ https://learn.ifs.name/d/leviathan2023/s/4-2-empirical-α-values/ https://learn.ifs.name/d/leviathan2023/s/5-related-work/ https://learn.ifs.name/d/wang2023/ https://learn.ifs.name/d/wang2023/s/1-introduction/ https://learn.ifs.name/d/wang2023/s/2-self-consistency-over-diverse-reasoning-paths/ https://learn.ifs.name/d/wang2023/s/3-1-experiment-setup/ https://learn.ifs.name/d/wang2023/s/3-2-main-results/ https://learn.ifs.name/d/wang2023/s/3-3-self-consistency-helps-when-chain-of-thought-hurts-performance/ https://learn.ifs.name/d/wang2023/s/3-4-compare-to-other-existing-approaches/ https://learn.ifs.name/d/wang2023/s/3-5-additional-studies/ https://learn.ifs.name/d/wang2023/s/5-conclusion-and-discussion/ https://learn.ifs.name/d/yao2023react/ https://learn.ifs.name/d/yao2023react/s/1-introduction/ https://learn.ifs.name/d/yao2023react/s/2-react-synergizing-reasoning-acting/ https://learn.ifs.name/d/yao2023react/s/3-1-setup/ https://learn.ifs.name/d/yao2023react/s/3-2-methods/ https://learn.ifs.name/d/yao2023react/s/3-3-results-and-observations/ https://learn.ifs.name/d/yao2023react/s/4-decision-making-tasks/ https://learn.ifs.name/d/yao2023react/s/6-conclusion/ https://learn.ifs.name/d/radford2023/ https://learn.ifs.name/d/radford2023/s/1-introduction/ https://learn.ifs.name/d/radford2023/s/2-1-data-processing/ https://learn.ifs.name/d/radford2023/s/2-2-model/ https://learn.ifs.name/d/radford2023/s/2-3-multitask-format/ https://learn.ifs.name/d/radford2023/s/3-2-evaluation-metrics/ https://learn.ifs.name/d/radford2023/s/3-3-english-speech-recognition/ https://learn.ifs.name/d/radford2023/s/3-4-multi-lingual-speech-recognition/ https://learn.ifs.name/d/radford2023/s/3-5-translation/ https://learn.ifs.name/d/radford2023/s/3-6-language-identification/ https://learn.ifs.name/d/radford2023/s/4-1-dataset-scaling/ https://learn.ifs.name/d/radford2023/s/4-3-multitask-and-multilingual-transfer/ https://learn.ifs.name/d/radford2023/s/a-1-strategies-for-reliable-long-form-transcription/ https://learn.ifs.name/d/kirchenbauer2023/ https://learn.ifs.name/d/kirchenbauer2023/s/1-introduction/ https://learn.ifs.name/d/kirchenbauer2023/s/1-2-a-caveat-the-difficulty-of-watermarking-low-entropy-sequences/ https://learn.ifs.name/d/kirchenbauer2023/s/2-a-simple-proof-of-concept/ https://learn.ifs.name/d/kirchenbauer2023/s/3-a-more-sophisticated-watermark/ https://learn.ifs.name/d/kirchenbauer2023/s/3-1-detecting-the-soft-watermark/ https://learn.ifs.name/d/kirchenbauer2023/s/4-analysis-of-the-soft-watermark/ https://learn.ifs.name/d/kirchenbauer2023/s/4-2-impact-on-quality-of-generated-text/ https://learn.ifs.name/d/kirchenbauer2023/s/5-private-watermarking/ https://learn.ifs.name/d/kirchenbauer2023/s/6-experiments/ https://learn.ifs.name/d/kirchenbauer2023/s/7-1-degradation-under-attack-span-replacement/ https://learn.ifs.name/d/kirchenbauer2023/s/8-related-work/ https://learn.ifs.name/d/touvron2023/ https://learn.ifs.name/d/touvron2023/s/1-introduction/ https://learn.ifs.name/d/touvron2023/s/2-1-pre-training-data/ https://learn.ifs.name/d/touvron2023/s/2-2-architecture/ https://learn.ifs.name/d/touvron2023/s/2-4-efficient-implementation/ https://learn.ifs.name/d/touvron2023/s/3-1-common-sense-reasoning/ https://learn.ifs.name/d/touvron2023/s/3-2-closed-book-question-answering/ https://learn.ifs.name/d/touvron2023/s/3-4-mathematical-reasoning/ https://learn.ifs.name/d/touvron2023/s/3-6-massive-multitask-language-understanding/ https://learn.ifs.name/d/touvron2023/s/4-instruction-finetuning/ https://learn.ifs.name/d/touvron2023/s/5-bias-toxicity-and-misinformation/ https://learn.ifs.name/d/touvron2023/s/6-carbon-footprint/ https://learn.ifs.name/d/schick2023/ https://learn.ifs.name/d/schick2023/s/1-introduction/ https://learn.ifs.name/d/schick2023/s/2-approach/ https://learn.ifs.name/d/schick2023/s/3-tools/ https://learn.ifs.name/d/schick2023/s/4-1-experimental-setup/ https://learn.ifs.name/d/schick2023/s/4-2-downstream-tasks/ https://learn.ifs.name/d/schick2023/s/4-3-language-modeling/ https://learn.ifs.name/d/schick2023/s/4-4-scaling-laws/ https://learn.ifs.name/d/schick2023/s/6-limitations/ https://learn.ifs.name/d/wang2023selfinstruct/ https://learn.ifs.name/d/wang2023selfinstruct/s/1-introduction/ https://learn.ifs.name/d/wang2023selfinstruct/s/2-1-defining-instruction-data/ https://learn.ifs.name/d/wang2023selfinstruct/s/2-2-automatic-instruction-data-generation/ https://learn.ifs.name/d/wang2023selfinstruct/s/2-3-finetuning-the-lm-to-follow-instructions/ https://learn.ifs.name/d/wang2023selfinstruct/s/3-self-instruct-data-from-gpt3/ https://learn.ifs.name/d/wang2023selfinstruct/s/4-3-experiment-1-zero-shot-generalization-on-superni-benchmark/ https://learn.ifs.name/d/wang2023selfinstruct/s/4-4-experiment-2-generalization-to-user-oriented-instructions-on-novel-tasks/ https://learn.ifs.name/d/wang2023selfinstruct/s/4-5-effect-of-data-size-and-quality/ https://learn.ifs.name/d/wang2023selfinstruct/s/5-related-work/ https://learn.ifs.name/d/wang2023selfinstruct/s/8-limitations/ https://learn.ifs.name/d/zhou2023/ https://learn.ifs.name/d/zhou2023/s/1-introduction/ https://learn.ifs.name/d/zhou2023/s/2-alignment-data/ https://learn.ifs.name/d/zhou2023/s/2-1-community-questions-and-answers/ https://learn.ifs.name/d/zhou2023/s/2-2-manually-authored-examples/ https://learn.ifs.name/d/zhou2023/s/3-training-lima/ https://learn.ifs.name/d/zhou2023/s/4-2-results/ https://learn.ifs.name/d/zhou2023/s/4-3-analysis/ https://learn.ifs.name/d/zhou2023/s/5-why-is-less-more-ablations-on-data-diversity-quality-and-quantity/ https://learn.ifs.name/d/zhou2023/s/6-multi-turn-dialogue/ https://learn.ifs.name/d/zhou2023/s/7-discussion/ https://learn.ifs.name/d/rafailov2023/ https://learn.ifs.name/d/rafailov2023/s/1-introduction/ https://learn.ifs.name/d/rafailov2023/s/3-preliminaries/ https://learn.ifs.name/d/rafailov2023/s/4-direct-preference-optimization/ https://learn.ifs.name/d/rafailov2023/s/5-1-your-language-model-is-secretly-a-reward-model/ https://learn.ifs.name/d/rafailov2023/s/5-2-instability-of-actor-critic-algorithms/ https://learn.ifs.name/d/rafailov2023/s/6-1-how-well-can-dpo-optimize-the-rlhf-objective/ https://learn.ifs.name/d/rafailov2023/s/6-2-can-dpo-scale-to-real-preference-datasets/ https://learn.ifs.name/d/rafailov2023/s/6-3-generalization-to-a-new-input-distribution/ https://learn.ifs.name/d/rafailov2023/s/6-4-validating-gpt-4-judgments-with-human-judgments/ https://learn.ifs.name/d/rafailov2023/s/7-discussion/ https://learn.ifs.name/d/dettmers2023/ https://learn.ifs.name/d/dettmers2023/s/1-introduction/ https://learn.ifs.name/d/dettmers2023/s/2-background/ https://learn.ifs.name/d/dettmers2023/s/3-qlora-finetuning/ https://learn.ifs.name/d/dettmers2023/s/4-qlora-vs-standard-finetuning/ https://learn.ifs.name/d/dettmers2023/s/5-pushing-the-chatbot-state-of-the-art-with-qlora/ https://learn.ifs.name/d/dettmers2023/s/7-limitations-and-discussion/ https://learn.ifs.name/d/yao2023tot/ https://learn.ifs.name/d/yao2023tot/s/1-introduction/ https://learn.ifs.name/d/yao2023tot/s/2-background/ https://learn.ifs.name/d/yao2023tot/s/3-tree-of-thoughts-deliberate-problem-solving-with-lm/ https://learn.ifs.name/d/yao2023tot/s/4-1-game-of-24/ https://learn.ifs.name/d/yao2023tot/s/4-2-creative-writing/ https://learn.ifs.name/d/yao2023tot/s/4-3-mini-crosswords/ https://learn.ifs.name/d/yao2023tot/s/6-discussion/ https://learn.ifs.name/d/schaeffer2023/ https://learn.ifs.name/d/schaeffer2023/s/1-introduction/ https://learn.ifs.name/d/schaeffer2023/s/2-alternative-explanation-for-emergent-abilities/ https://learn.ifs.name/d/schaeffer2023/s/3-analyzing-instructgpt-gpt-3’s-emergent-arithmetic-abilities/ https://learn.ifs.name/d/schaeffer2023/s/4-meta-analysis-of-claimed-emergent-abilities/ https://learn.ifs.name/d/schaeffer2023/s/5-inducing-emergent-abilities-in-networks-on-vision-tasks/ https://learn.ifs.name/d/schaeffer2023/s/6-limitations/ https://learn.ifs.name/d/schaeffer2023/s/7-related-work/ https://learn.ifs.name/d/schaeffer2023/s/8-discussion/ https://learn.ifs.name/d/zheng2023/ https://learn.ifs.name/d/zheng2023/s/1-introduction/ https://learn.ifs.name/d/zheng2023/s/2-2-mt-bench/ https://learn.ifs.name/d/zheng2023/s/2-3-chatbot-arena/ https://learn.ifs.name/d/zheng2023/s/3-1-types-of-llm-as-a-judge/ https://learn.ifs.name/d/zheng2023/s/3-3-limitations-of-llm-as-a-judge/ https://learn.ifs.name/d/zheng2023/s/3-4-addressing-limitations/ https://learn.ifs.name/d/zheng2023/s/3-5-multi-turn-judge/ https://learn.ifs.name/d/zheng2023/s/4-2-high-agreement-between-gpt-4-and-humans/ https://learn.ifs.name/d/zheng2023/s/5-human-preference-benchmark-and-standardized-benchmark/ https://learn.ifs.name/d/zheng2023/s/6-discussion/ https://learn.ifs.name/d/muennighoff2023/ https://learn.ifs.name/d/muennighoff2023/s/1-introduction/ https://learn.ifs.name/d/muennighoff2023/s/2-background/ https://learn.ifs.name/d/muennighoff2023/s/3-method/ https://learn.ifs.name/d/muennighoff2023/s/4-experimental-setup/ https://learn.ifs.name/d/muennighoff2023/s/5-results-resource-allocation-for-data-constrained-scaling/ https://learn.ifs.name/d/muennighoff2023/s/6-results-resource-return-for-data-constrained-scaling/ https://learn.ifs.name/d/muennighoff2023/s/7-results-complementary-strategies-for-obtaining-additional-data/ https://learn.ifs.name/d/lightman2024/ https://learn.ifs.name/d/lightman2024/s/1-introduction/ https://learn.ifs.name/d/lightman2024/s/2-1-scope/ https://learn.ifs.name/d/lightman2024/s/2-4-data-collection/ https://learn.ifs.name/d/lightman2024/s/2-6-process-supervised-reward-models/ https://learn.ifs.name/d/lightman2024/s/3-large-scale-supervision/ https://learn.ifs.name/d/lightman2024/s/4-1-process-vs-outcome-supervision/ https://learn.ifs.name/d/lightman2024/s/4-2-active-learning/ https://learn.ifs.name/d/lightman2024/s/5-ood-generalization/ https://learn.ifs.name/d/lightman2024/s/6-1-credit-assignment/ https://learn.ifs.name/d/lightman2024/s/6-2-alignment-impact/ https://learn.ifs.name/d/lightman2024/s/7-related-work/ https://learn.ifs.name/d/wei2023/ https://learn.ifs.name/d/wei2023/s/1-introduction/ https://learn.ifs.name/d/wei2023/s/2-background-safety-trained-language-models-and-jailbreak-attacks/ https://learn.ifs.name/d/wei2023/s/3-1-competing-objectives/ https://learn.ifs.name/d/wei2023/s/3-2-mismatched-generalization/ https://learn.ifs.name/d/wei2023/s/4-empirical-evaluation-of-jailbreak-methods/ https://learn.ifs.name/d/wei2023/s/5-implications-for-defense/ https://learn.ifs.name/d/zou2023/ https://learn.ifs.name/d/zou2023/s/1-introduction/ https://learn.ifs.name/d/zou2023/s/2-1-producing-affirmative-responses/ https://learn.ifs.name/d/zou2023/s/2-2-greedy-coordinate-gradient-based-search/ https://learn.ifs.name/d/zou2023/s/2-3-universal-multi-prompt-and-multi-model-attacks/ https://learn.ifs.name/d/zou2023/s/3-experimental-results-direct-and-transfer-attacks/ https://learn.ifs.name/d/zou2023/s/3-1-attacks-on-white-box-models/ https://learn.ifs.name/d/zou2023/s/3-2-transfer-attacks/ https://learn.ifs.name/d/zou2023/s/5-conclusion-and-future-work/ https://learn.ifs.name/d/zou2023/s/6-ethics-and-broader-impact/ https://learn.ifs.name/d/kwon2023/ https://learn.ifs.name/d/kwon2023/s/1-introduction/ https://learn.ifs.name/d/kwon2023/s/2-2-llm-service-and-autoregressive-generation/ https://learn.ifs.name/d/kwon2023/s/3-memory-challenges-in-llm-serving/ https://learn.ifs.name/d/kwon2023/s/4-1-pagedattention/ https://learn.ifs.name/d/kwon2023/s/4-2-kv-cache-manager/ https://learn.ifs.name/d/kwon2023/s/4-4-application-to-other-decoding-scenarios/ https://learn.ifs.name/d/kwon2023/s/4-5-scheduling-and-preemption/ https://learn.ifs.name/d/kwon2023/s/6-2-basic-sampling/ https://learn.ifs.name/d/kwon2023/s/7-1-kernel-microbenchmark/ https://learn.ifs.name/d/kwon2023/s/7-2-impact-of-block-size/ https://learn.ifs.name/d/kwon2023/s/7-3-comparing-recomputation-and-swapping/