一种基于混合神经网络的命名实体识别与共指消解联合模型

A Joint Model of Named Entity Recognition and Coreference Resolution Based on Hybrid Neural Network

命名实体识别与共指消解均依赖于对实体相邻文本信息的学习,本文提出一种基于混合神经网络的命名实体识别与共指消解联合模型,共用双向长短时记忆模型LSTM编码层对输入序列中每个词前后方向上下文信息进行编码,并通过训练学习得到上下文信息传递到前馈神经网络FFNN模型以提高共指消解精度,通过将领域文档及篇章语义向量加入FFNN,改进共指消解算法并优化共指消解模型.基于领域文本数据集进行联合模型训练,实验结果表明该联合模型可以有效地提高共指消解精度.

Considering that both named entity recognition and coreference resolution depend on the same context of the entity word,this paper proposes a hybrid neural network model to settle these problems which contains a named entity recognition(NER)module and a coreference resolution(CR)module.NER and CR share the same bidirectional LSTM encoding layer,which is used to encode each input word by taking into account the context on both sides of the word.The contextual information of entities obtained in BiLSTM encoding layer further pass through to FFNN module to improve the coreference resolution.Furthermore,by adding domain documents and chapter semantic vectors to FFNN,the coreference resolution algorithm is improved and the coreference resolution model is optimized.Finally,we conduct experiments on the domain dataset to verify the effectiveness of our method.The joint model can effectively improve the accuracy of coreference resolution task.