Deep contextualized word representations
Peters et al., 2018, Deep contextualized word representations (Proceedings of the 2018 Conference of the North American Chapter of ACL: Human Language Technologies (NAACL-HLT 2018))
Subscriber deck — free during early access
1 cards in “4 Evaluation” · whole deck
4 Evaluation
- How much did ELMo improve each task?Over strong baselines on test sets:
task baseline + ELMo rel. error ↓ SQuAD (F1) 81.1 85.8 24.9% SNLI (acc.) 88.0 88.7 5.8% SRL (F1) 81.4 84.6 17.2% Coref (avg F1) 67.2 70.4 9.8% NER (F1) 90.15 92.22 21% SST-5 (acc.) 51.4 54.7 6.8% - Peters et al., 2018, Deep contextualized word representations (Proceedings of the 2018 Conference of the North American Chapter of ACL: Human Language Technologies (NAACL-HLT 2018)), §4, pp. 2230–2232
Source
- Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee and Luke Zettlemoyer. 2018. Deep contextualized word representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2018), pp. 2227–2237. License: CC BY 4.0. Flashcards adapted from this work. doi:10.18653/v1/N18-1202 https://aclanthology.org/N18-1202/