A Joint Neural Model for Fine-Grained Named Entity Classification of Wikipedia Articles

• SUZUKI Masatoshi

  Tohoku University

• MATSUDA Koji

  Tohoku University

• SEKINE Satoshi

  Language Craft Inc RIKEN Center for Advanced Intelligence Project

• OKAZAKI Naoaki

  Tokyo Institute of Technology

• INUI Kentaro

  Tohoku University RIKEN Center for Advanced Intelligence Project

抄録

This paper addresses the task of assigning labels of fine-grained named entity (NE) types to Wikipedia articles. Information of NE types are useful when extracting knowledge of NEs from natural language text. It is common to apply an approach based on supervised machine learning to named entity classification. However, in a setting of classifying into fine-grained types, one big challenge is how to alleviate the data sparseness problem since one may obtain far fewer instances for each fine-grained types. To address this problem, we propose two methods. First, we introduce a multi-task learning framework, in which NE type classifiers are all jointly trained with a neural network. The neural network has a hidden layer, where we expect that effective combinations of input features are learned across different NE types. Second, we propose to extend the input feature set by exploiting the hyperlink structure of Wikipedia. While most of previous studies are focusing on engineering features from the articles' contents, we observe that the information of the contexts the article is mentioned can also be a useful clue for NE type classification. Concretely, we propose to learn article vectors (i.e. entity embeddings) from Wikipedia's hyperlink structure using a Skip-gram model. Then we incorporate the learned article vectors into the input feature set for NE type classification. To conduct large-scale practical experiments, we created a new dataset containing over 22,000 manually labeled articles. With the dataset, we empirically show that both of our ideas gained their own statistically significant improvement separately in classification accuracy. Moreover, we show that our proposed methods are particularly effective in labeling infrequent NE types. We've made the learned article vectors publicly available. The labeled dataset is available if one contacts the authors.

収録刊行物

• IEICE Transactions on Information and Systems

  IEICE Transactions on Information and Systems E101.D (1), 73-81, 2018

  一般社団法人 電子情報通信学会

キーワード

• named entity classification
• wikipedia
• multi-task learning
• neural network

詳細情報

• CRID: 1390001204380995456
• NII論文ID: 130006301194
• DOI: 10.1587/transinf.2017swp0005
• ISSN: 17451361
• ISSN: 09168532
• Web Site: https://www.jstage.jst.go.jp/article/transinf/E101.D/1/E101.D_2017SWP0005/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可