Multilingual SubEvent Relation Extraction: A Novel Dataset and Structure Induction Method

Viet Lai, Hieu Man, Linh Ngo, Franck Dernoncourt, Thien Nguyen


Abstract
Subevent Relation Extraction (SRE) is a task in Information Extraction that aims to recognize spatial and temporal containment relations between event mentions in text. Recent methods have utilized pre-trained language models to represent input texts for SRE. However, a key issue in existing SRE methods is the employment of sequential order of words in texts to feed into representation learning methods, thus unable to explicitly focus on important context words and their interactions to enhance representations. In this work, we introduce a new method for SRE that learns to induce effective graph structures for input texts to boost representation learning. Our method features a word alignment framework with dependency paths and optimal transport to identify important context words to form effective graph structures for SRE. In addition, to enable SRE research on non-English languages, we present a new multilingual SRE dataset for five typologically different languages. Extensive experiments reveal the state-of-the-art performance for our method on different datasets and languages.
Anthology ID:
2022.findings-emnlp.407
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5559–5570
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.407
DOI:
10.18653/v1/2022.findings-emnlp.407
Bibkey:
Cite (ACL):
Viet Lai, Hieu Man, Linh Ngo, Franck Dernoncourt, and Thien Nguyen. 2022. Multilingual SubEvent Relation Extraction: A Novel Dataset and Structure Induction Method. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5559–5570, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Multilingual SubEvent Relation Extraction: A Novel Dataset and Structure Induction Method (Lai et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.407.pdf