Deep Reinforcement Learning for Chinese Zero pronoun Resolution
This work solves a coreference resolution problem for Chinese natural language processing, representing an incremental improvement over existing methods.
The paper tackled the problem of Chinese zero pronoun resolution by addressing the short-sightedness of deep neural network models that make local decisions, and it integrated local and global decision-making using deep reinforcement learning to improve performance, achieving state-of-the-art results on the OntoNotes 5.0 dataset.
Deep neural network models for Chinese zero pronoun resolution learn semantic information for zero pronoun and candidate antecedents, but tend to be short-sighted---they often make local decisions. They typically predict coreference chains between the zero pronoun and one single candidate antecedent one link at a time, while overlooking their long-term influence on future decisions. Ideally, modeling useful information of preceding potential antecedents is critical when later predicting zero pronoun-candidate antecedent pairs. In this study, we show how to integrate local and global decision-making by exploiting deep reinforcement learning models. With the help of the reinforcement learning agent, our model learns the policy of selecting antecedents in a sequential manner, where useful information provided by earlier predicted antecedents could be utilized for making later coreference decisions. Experimental results on OntoNotes 5.0 dataset show that our technique surpasses the state-of-the-art models.