Information Extraction: Relations, Events, and Time

Introduction

1. What is information extraction (IE)?
   Turning unstructured information embedded in texts into structured data, e.g. to populate a relational database for further processing.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 21, Introduction, p. 473
2. What are the main IE tasks introduced in the chapter?
   Relation extraction (semantic relations between entities), event extraction, temporal expression recognition and normalization, temporal ordering of events, and template filling.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 21, Introduction, p. 473
3. What is a knowledge graph?
   A dataset of structured relational knowledge, used e.g. by search engines to present information to users; relation extraction helps populate it.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 21, Introduction, p. 473
4. What is template filling?
   Finding recurring stereotypical events or situations in documents and filling the slots of a template with text segments or inferred concepts (times, amounts, ontology entities).

   FARE-RAISE ATTEMPT
   LEAD AIRLINE	United Airlines
   AMOUNT	$6
   EFFECTIVE DATE	2006-10-26
   FOLLOWER	American Airlines

   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 21, Introduction, pp. 473–474