Joint Coreference Resolution and Character Linking for Multiparty Conversation

TL;DR

This paper introduces C$^2$, a joint model for coreference resolution and character linking in multiparty conversations, leveraging mutual information to improve both tasks' accuracy.

Contribution

The paper presents a novel joint learning approach that simultaneously addresses coreference resolution and character linking, outperforming previous methods.

Findings

C$^2$ significantly outperforms previous models on both tasks.

Joint modeling improves the accuracy of character linking and coreference resolution.

Analysis shows the effectiveness of the integrated approach and hyper-parameter tuning.

Abstract

Character linking, the task of linking mentioned people in conversations to the real world, is crucial for understanding the conversations. For the efficiency of communication, humans often choose to use pronouns (e.g., "she") or normal phrases (e.g., "that girl") rather than named entities (e.g., "Rachel") in the spoken language, which makes linking those mentions to real people a much more challenging than a regular entity linking task. To address this challenge, we propose to incorporate the richer context from the coreference relations among different mentions to help the linking. On the other hand, considering that finding coreference clusters itself is not a trivial task and could benefit from the global character information, we propose to jointly solve these two tasks. Specifically, we propose C$^2$, the joint learning model of Coreference resolution and Character linking. The experimental results demonstrate that C$^2$ can significantly outperform previous works on both tasks. Further analyses are conducted to analyze the contribution of all modules in the proposed model and the effect of all hyper-parameters.