A Survey on Pronoun Coreference Resolution

PhD Qualifying Examination


Title: "A Survey on Pronoun Coreference Resolution"

by

Mr. Hongming Zhang


Abstract:

Pronoun Coreference Resolution (PCR) is the task of resolving pronominal 
expressions to all mentions they refer to. In most of the cases, pronouns refer 
to noun phrases. Compared with the general coreference resolution task, PCR is 
focusing on the coreference relation prediction rather than the mention 
detection. As one crucial natural language understanding (NLU) task, PCR is 
quite challenging for all existing models, which motivates us to survey 
existing approaches and think about how to do better. In this survey, we first 
introduce representative datasets and models for the ordinary pronoun 
coreference resolution task. After that, we focus on introducing recent 
progress on hard pronoun coreference resolution problems (e.g., Winograd Schema 
Challenge) to analyze how well current models can understand commonsense 
knowledge. In the end, we introduce other related research topics about the 
pronoun coreference resolution task (e.g., PCR for machine translation, Chinese 
zero pronoun coreference resolution, and visual-aware PCR). To conclude, in 
recent years, the community has achieved great progress in resolving pronouns, 
but there are still many unsolved problems (e.g., cross-domain, explainable 
PCR, and multi-model PCR) worth exploring in the future.


Date:			Monday, 6 January 2020

Time:                  	10:00am - 12:00noon

Venue:                  Room 3494
                         Lifts 25/26

Committee Members:	Dr. Yangqiu Song (Supervisor)
 			Dr. Wilfred Ng (Chairperson)
 			Dr. Xiaojun Ma
 			Prof. Tong Zhang (MATH)


**** ALL are Welcome ****