Minimize exposure bias of seq2seq models in joint entity and relation extraction

Ranran Haoran Zhang, Qianying Liu, Aysa Xuemo Fan, Heng Ji, Daojian Zeng, Fei Cheng, Daisuke Kawahara, Sadao Kurohashi

研究成果: Conference contribution

6 被引用数 (Scopus)

抄録

Joint entity and relation extraction aims to extract relation triplets from plain text directly. Prior work leverages Sequence-to-Sequence (Seq2Seq) models for triplet sequence generation. However, Seq2Seq enforces an unnecessary order on the unordered triplets and involves a large decoding length associated with error accumulation. These methods introduce exposure bias, which may cause the models overfit to the frequent label combination, thus limiting the generalization ability. We propose a novel Sequence-to-UnorderedMulti-Tree (Seq2UMTree) model to minimize the effects of exposure bias by limiting the decoding length to three within a triplet and removing the order among triplets. We evaluate our model on two datasets, DuIE and NYT, and systematically study how exposure bias alters the performance of Seq2Seq models. Experiments show that the state-of-the-art Seq2Seq model overfits to both datasets while Seq2UMTree shows significantly better generalization. Our code is available at https://github.com/WindChimeRan/OpenJERE.

本文言語English
ホスト出版物のタイトルFindings of the Association for Computational Linguistics Findings of ACL
ホスト出版物のサブタイトルEMNLP 2020
出版社Association for Computational Linguistics (ACL)
ページ236-246
ページ数11
ISBN(電子版)9781952148903
出版ステータスPublished - 2020
イベントFindings of the Association for Computational Linguistics, ACL 2020: EMNLP 2020 - Virtual, Online
継続期間: 2020 11月 162020 11月 20

出版物シリーズ

名前Findings of the Association for Computational Linguistics Findings of ACL: EMNLP 2020

Conference

ConferenceFindings of the Association for Computational Linguistics, ACL 2020: EMNLP 2020
CityVirtual, Online
Period20/11/1620/11/20

ASJC Scopus subject areas

  • 情報システム
  • コンピュータ サイエンスの応用
  • 計算理論と計算数学

フィンガープリント

「Minimize exposure bias of seq2seq models in joint entity and relation extraction」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