Neural architectures for fine-grained entity type classification

Sonse Shimaoka, Pontus Stenetorp, Kentaro Inui, Sebastian Riedel

研究成果: Conference contribution

39 被引用数 (Scopus)

抄録

In this work, we investigate several neural network architectures for fine-grained entity type classification and make three key contributions. Despite being a natural comparison and addition, previous work on attentive neural architectures have not considered hand-crafted features and we combine these with learnt features and establish that they complement each other. Additionally, through quantitative analysis we establish that the attention mechanism learns to attend over syntactic heads and the phrase containing the mention, both of which are known to be strong hand-crafted features for our task. We introduce parameter sharing between labels through a hierarchical encoding method, that in lowdimensional projections show clear clusters for each type hierarchy. Lastly, despite using the same evaluation dataset, the literature frequently compare models trained using different data. We demonstrate that the choice of training data has a drastic impact on performance, which decreases by as much as 9.85% loose micro F1 score for a previously proposed method. Despite this discrepancy, our best model achieves state-of-the-art results with 75.36% loose micro F1 score on the well-established FIGER (GOLD) dataset and we report the best results for models trained using publicly available data for the OntoNotes dataset with 64.93% loose micro F1 score.

本文言語English
ホスト出版物のタイトルLong Papers - Continued
出版社Association for Computational Linguistics (ACL)
ページ1271-1280
ページ数10
ISBN(電子版)9781510838604
DOI
出版ステータスPublished - 2017
イベント15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spain
継続期間: 2017 4 32017 4 7

出版物シリーズ

名前15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference
1

Other

Other15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
国/地域Spain
CityValencia
Period17/4/317/4/7

ASJC Scopus subject areas

  • 言語学および言語
  • 言語および言語学

フィンガープリント

「Neural architectures for fine-grained entity type classification」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル