融入篇章信息的文学作品命名实体识别

Document-level Named Entity Recognition for Literary Texts

命名实体识别是文学作品智能分析的基础性工作,当前文学领域命名实体识别的研究还较薄弱,一个主要原因是缺乏标注语料。该文从金庸小说入手,对两部小说180余万字进行了命名实体的标注,共标注4类实体,共计5万多个。针对小说文本的特点,该文提出融入篇章信息的命名实体识别模型,引入篇章字典保存汉字的历史状态,利用可信度计算融合BiGRU-CRF与Transformer模型。实验结果表明,利用篇章信息有效提升了命名实体识别的效果。最后,该文还探讨了命名实体识别在小说社会网络构建中的应用。

Named entity recognition is essential to the intelligent analysis of literary works.We annotate over 50 thousands named entities of four types from about 1.8 million words of two Jin Yong’s novels.According to the characteristics of novel text,this paper proposes a document-level named entity recognition model with a dictionary to record the historical state of Chinese characters.We use confidence estimation to fuse BiGRU-CRF and Transformer model.The experimental results show that the proposed method can effectively improve the performance of named entity recognition.