Coreference Resolution and Entity Linking

Introduction

1. What are mentions (referring expressions), referents, and coreference?
   Mentions are linguistic expressions like her or Victoria Chen; the referent is the discourse entity referred to. Two or more mentions that refer to the same discourse entity corefer.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Introduction, p. 539
2. Give three applications that need coreference resolution.
   A dialogue system resolving “I’ll take the second one” to a flight it listed; QA knowing who she is in “She was born in Warsaw”; MT from a pro-drop language like Spanish choosing “he says” vs “she says”.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Introduction, p. 539
3. What is a discourse model, and what does it mean for a referent to be evoked or accessed?
   A mental model built incrementally while interpreting a text, holding the entities referred to, their properties and relations. A first mention evokes a representation into the model; later mentions access it.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Introduction, p. 539
4. Define anaphora, anaphor, antecedent and singleton.
   Anaphora: reference to an entity previously introduced; the referring expression is an anaphor; the prior coreferring mention is its antecedent. A singleton is an entity mentioned only once.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Introduction, p. 540
5. What is coreference resolution, and what two subtasks does it comprise?
   Determining whether mentions corefer, producing coreference chains (clusters). Subtasks, often done jointly: (1) identify the mentions, (2) cluster them into chains/discourse entities.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Introduction, p. 540
6. Find the coreference chains in: “Victoria Chen, CFO of Megabucks Banking, saw her pay jump to $2.3 million, as the 38-year-old became the company’s president. It is widely known that she came to Megabucks from rival Lotsabucks.”

   1	{Victoria Chen, her, the 38-year-old, she}
   2	{Megabucks Banking, the company, Megabucks}
   3	{her pay}
   4	{Lotsabucks}

   Mentions can nest: her is inside her pay, a different entity.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Introduction, p. 540
7. What is entity linking (entity resolution), and what is wikification?
   Mapping a discourse entity to a real-world individual in an ontology (e.g. Washington: the state, the city, or George Washington). Wikification uses Wikipedia pages as the entity ids.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Introduction, pp. 540–541
8. What is event coreference?
   Deciding whether two event mentions refer to the same event, e.g. buy and acquisition in two sentences about AMD and ATI. Event mentions are harder to detect since they can be verbal or nominal.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Introduction, p. 541
9. What is discourse deixis?
   An anaphor referring back to a discourse segment: after “According to Soleil, Beau just opened a restaurant”, that can be a speech act (“that turned out to be a lie”), a proposition (“that was false”) or a manner of description.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Introduction, p. 541