Information Extraction: Relations, Events, and Time

Historical notes

1. What drove progress in information extraction historically?
   Early template filling (DeJong’s Frump), the US-government MUC conferences, then machine learning and sequence labeling (HMMs, MEMMs, CRFs, neural), and shared evaluations: ACE, TAC KBP (slot filling), SemEval.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 21, Historical notes, p. 497
2. Who introduced distant supervision and Open IE systems?
   Mintz et al. (2009) coined distant supervision (similar ideas existed as “weakly labeled data”); Open IE systems include KnowItAll, TextRunner and ReVerb.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 21, Historical notes, p. 497