Exophoric Pronoun Resolution in Dialogues with Topic Regularization

09/10/2021
by   Xintong Yu, et al.
0

Resolving pronouns to their referents has long been studied as a fundamental natural language understanding problem. Previous works on pronoun coreference resolution (PCR) mostly focus on resolving pronouns to mentions in text while ignoring the exophoric scenario. Exophoric pronouns are common in daily communications, where speakers may directly use pronouns to refer to some objects present in the environment without introducing the objects first. Although such objects are not mentioned in the dialogue text, they can often be disambiguated by the general topics of the dialogue. Motivated by this, we propose to jointly leverage the local context and global topics of dialogues to solve the out-of-text PCR problem. Extensive experiments demonstrate the effectiveness of adding topic regularization for resolving exophoric pronouns.

READ FULL TEXT

page 12

page 13

research
03/03/2021

Natural Language Understanding for Argumentative Dialogue Systems in the Opinion Building Domain

This paper introduces a natural language understanding (NLU) framework f...
research
01/29/2023

Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality

Dialogue summarization aims to condense a given dialogue into a simple a...
research
12/02/2019

KRM-based Dialogue Management

A KRM-based dialogue management (DM) is proposed using to implement huma...
research
09/01/2019

What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues

Grounding a pronoun to a visual object it refers to requires complex rea...
research
09/03/2017

Topic Independent Identification of Agreement and Disagreement in Social Media Dialogue

Research on the structure of dialogue has been hampered for years becaus...
research
09/18/2023

Multi-turn Dialogue Comprehension from a Topic-aware Perspective

Dialogue related Machine Reading Comprehension requires language models ...
research
09/01/2019

A Dataset of General-Purpose Rebuttal

In Natural Language Understanding, the task of response generation is us...

Please sign up or login with your details

Forgot password? Click here to reset