SPNet: A Serial and Parallel Convolutional Neural Network algorithm for the cross-language coreference resolution.

Current models of coreference resolution always neglect the importance of hidden feature extraction, accurate scoring framework design, and the long-term influence of preceding potential antecedents on future decision-making. However, these aspects play vital roles in scoring the likelihood of coreference between an anaphora and its' real antecedent. In this paper, we present a novel model named Serial and Parallel Convolutional Neural Network (SPNet). Based on the SPNet, two kinds of resolvers are proposed. Given the characteristics of reinforcement learning, we joint the reinforcement learning framework and the SPNet to solve the problem of Chinese zero pronoun resolution. What is more, we make some fine-tuning on the SPNet and propose a new resolver combined with the end-to-end framework to solve the problem of coreference resolution. The experiments are conducted on the CoNLL-2012 dataset and the results show that our model is effective. Our model achieves excellent performance in the Chinese zero pronoun resolution task. On the other hand, compared with our baseline, our model also has an improvement of 0.3% in coreference resolution task. • A novel model which named SPNet is proposed. This model can automatically extract effective high-level semantic features and realize multi-level features fusion. • In this paper, the SPNet is combined with reinforcement learning to solve the Chinese zero pronoun resolution. Based on SPNet, T-SPNet is proposed, and we combine them to solve the problem of coreference resolution. • Our model achieves excellent performance in the Chinese zero anaphora resolution and gains a meaningful improvement in the task of coreference resolution. [ABSTRACT FROM AUTHOR]