Neural Coreference Resolution based on Reinforcement Learning
This addresses coreference resolution for natural language processing applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles coreference resolution by proposing a reinforcement learning actor-critic-based neural system that jointly handles mention detection and clustering, achieving state-of-the-art performance on the CoNLL-2012 English Test Set.
The target of a coreference resolution system is to cluster all mentions that refer to the same entity in a given context. All coreference resolution systems need to solve two subtasks; one task is to detect all of the potential mentions, and the other is to learn the linking of an antecedent for each possible mention. In this paper, we propose a reinforcement learning actor-critic-based neural coreference resolution system, which can achieve both mention detection and mention clustering by leveraging an actor-critic deep reinforcement learning technique and a joint training algorithm. We experiment on the BERT model to generate different input span representations. Our model with the BERT span representation achieves the state-of-the-art performance among the models on the CoNLL-2012 Shared Task English Test Set.