Joint Coreference Resolution and Character Linking for Multiparty Conversation
This work addresses the problem of improving character linking in conversations for applications like dialogue understanding, though it appears incremental as it builds on existing tasks.
The paper tackles the challenge of linking people mentioned in multiparty conversations to real-world entities, especially when pronouns or vague phrases are used instead of named entities, by proposing a joint learning model called C^2 that integrates coreference resolution and character linking, and it significantly outperforms previous works on both tasks.
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.