Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields

TL;DR

This paper introduces Transformer-GCRF, a novel model combining Transformer networks with General Conditional Random Fields to improve the recovery of dropped pronouns in Chinese conversations by modeling inter-utterance dependencies.

Contribution

The paper proposes a new framework that integrates Transformer and GCRF to better model pronoun dependencies, outperforming existing methods in Chinese dropped pronoun recovery.

Findings

Transformer-GCRF outperforms state-of-the-art models.

GCRF effectively captures inter-utterance pronoun dependencies.

Model improves pronoun recovery accuracy on Chinese datasets.

Abstract

Pronouns are often dropped in Chinese conversations and recovering the dropped pronouns is important for NLP applications such as Machine Translation. Existing approaches usually formulate this as a sequence labeling task of predicting whether there is a dropped pronoun before each token and its type. Each utterance is considered to be a sequence and labeled independently. Although these approaches have shown promise, labeling each utterance independently ignores the dependencies between pronouns in neighboring utterances. Modeling these dependencies is critical to improving the performance of dropped pronoun recovery. In this paper, we present a novel framework that combines the strength of Transformer network with General Conditional Random Fields (GCRF) to model the dependencies between pronouns in neighboring utterances. Results on three Chinese conversation datasets show that the Transformer-GCRF model outperforms the state-of-the-art dropped pronoun recovery models. Exploratory analysis also demonstrates that the GCRF did help to capture the dependencies between pronouns in neighboring utterances, thus contributes to the performance improvements.