Recovering Dropped Pronouns in Chinese Conversations via Modeling Their Referents

TL;DR

This paper introduces an end-to-end neural network with structured attention to recover dropped pronouns in Chinese conversations, significantly improving referent resolution in various conversational genres.

Contribution

The work presents a novel neural model that effectively models referents of dropped pronouns using structured attention at multiple levels, advancing Chinese pronoun recovery.

Findings

Significant improvement over state-of-the-art methods

Effective modeling of referents using structured attention

Robust performance across different conversational genres

Abstract

Pronouns are often dropped in Chinese sentences, and this happens more frequently in conversational genres as their referents can be easily understood from context. Recovering dropped pronouns is essential to applications such as Information Extraction where the referents of these dropped pronouns need to be resolved, or Machine Translation when Chinese is the source language. In this work, we present a novel end-to-end neural network model to recover dropped pronouns in conversational data. Our model is based on a structured attention mechanism that models the referents of dropped pronouns utilizing both sentence-level and word-level information. Results on three different conversational genres show that our approach achieves a significant improvement over the current state of the art.