Modeling Document-Level Context for Event Detection via Important Context Selection

Amir Pouran Ben Veyseh, Minh Van Nguyen, Nghia Ngo Trung, Bonan Min, Thien Huu Nguyen


Abstract
The task of Event Detection (ED) in Information Extraction aims to recognize and classify trigger words of events in text. The recent progress has featured advanced transformer-based language models (e.g., BERT) as a critical component in state-of-the-art models for ED. However, the length limit for input texts is a barrier for such ED models as they cannot encode long-range document-level context that has been shown to be beneficial for ED. To address this issue, we propose a novel method to model document-level context for ED that dynamically selects relevant sentences in the document for the event prediction of the target sentence. The target sentence will be then augmented with the selected sentences and consumed entirely by transformer-based language models for improved representation learning for ED. To this end, the REINFORCE algorithm is employed to train the relevant sentence selection for ED. Several information types are then introduced to form the reward function for the training process, including ED performance, sentence similarity, and discourse relations. Our extensive experiments on multiple benchmark datasets reveal the effectiveness of the proposed model, leading to new state-of-the-art performance.
Anthology ID:
2021.emnlp-main.439
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5403–5413
Language:
URL:
https://aclanthology.org/2021.emnlp-main.439
DOI:
10.18653/v1/2021.emnlp-main.439
Bibkey:
Cite (ACL):
Amir Pouran Ben Veyseh, Minh Van Nguyen, Nghia Ngo Trung, Bonan Min, and Thien Huu Nguyen. 2021. Modeling Document-Level Context for Event Detection via Important Context Selection. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5403–5413, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Modeling Document-Level Context for Event Detection via Important Context Selection (Pouran Ben Veyseh et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.emnlp-main.439.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2021.emnlp-main.439.mp4