Coreference Resolution and Entity Linking

Historical notes

1. Who founded the discourse-model view of coreference?
   Karttunen (1969) formulated the discourse model; Bonnie Webber’s 1978 dissertation explored how entities are represented in it and how they license later reference.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Historical notes, p. 566
2. How does the simplified Hobbs algorithm search for a pronoun’s antecedent?
   Through NPs: (i) the current sentence right to left from the pronoun, (ii) the previous sentence left to right, (iii) two sentences back left to right, (iv) the current sentence left to right after the pronoun (cataphora). Pick the first NP agreeing in number, gender and person.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Historical notes, pp. 566–567
3. How did the MUC competitions shape coreference research?
   They focused on identity coreference only (ignoring bridging, metonymy, part–whole) and pushed the field toward supervised learning and the MUC metric.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Historical notes, p. 567
4. How can coreference and entity linking help each other?
   Coreference supplies more surface forms for linking; linking adds encyclopedic knowledge to coreference, e.g. that Donald Tsang is a president helps resolve the President.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Historical notes, p. 568
5. What coreference relations go beyond identity?
   Metonymy (Washington for the US) and refocused referents, e.g. “in France the president is elected for seven years, while in the United States he is elected for four”: different individuals.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 24, Historical notes, p. 568