Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder

Xi Xiangyu, Wei Ye, Shikun Zhang, Quanxiu Wang, Huixing Jiang, Wei Wu


Abstract
Capturing interactions among event arguments is an essential step towards robust event argument extraction (EAE). However, existing efforts in this direction suffer from two limitations: 1) The argument role type information of contextual entities is mainly utilized as training signals, ignoring the potential merits of directly adopting it as semantically rich input features; 2) The argument-level sequential semantics, which implies the overall distribution pattern of argument roles over an event mention, is not well characterized. To tackle the above two bottlenecks, we formalize EAE as a Seq2Seq-like learning problem for the first time, where a sentence with a specific event trigger is mapped to a sequence of event argument roles. A neural architecture with a novel Bi-directional Entity-level Recurrent Decoder (BERD) is proposed to generate argument roles by incorporating contextual entities’ argument role predictions, like a word-by-word text generation process, thereby distinguishing implicit argument distribution patterns within an event more accurately.
Anthology ID:
2021.acl-long.18
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
210–219
Language:
URL:
https://aclanthology.org/2021.acl-long.18
DOI:
10.18653/v1/2021.acl-long.18
Bibkey:
Cite (ACL):
Xi Xiangyu, Wei Ye, Shikun Zhang, Quanxiu Wang, Huixing Jiang, and Wei Wu. 2021. Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 210–219, Online. Association for Computational Linguistics.
Cite (Informal):
Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder (Xiangyu et al., ACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.18.pdf