CLSep 10, 2021

Exophoric Pronoun Resolution in Dialogues with Topic Regularization

arXiv:2109.04787v1661 citations
Originality Incremental advance
AI Analysis

This addresses a gap in pronoun coreference resolution for daily communications, though it is incremental by extending existing methods to handle exophoric scenarios.

The paper tackles the problem of resolving exophoric pronouns in dialogues, which refer to objects not mentioned in the text, by jointly using local context and global topics, showing effectiveness through extensive experiments.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes