Integrating Deep Event-Level and Script-Level Information for Script Event Prediction

Long Bai, Saiping Guan, Jiafeng Guo, Zixuan Li, Xiaolong Jin, Xueqi Cheng


Abstract
Scripts are structured sequences of events together with the participants, which are extracted from the texts. Script event prediction aims to predict the subsequent event given the historical events in the script. Two kinds of information facilitate this task, namely, the event-level information and the script-level information. At the event level, existing studies view an event as a verb with its participants, while neglecting other useful properties, such as the state of the participants. At the script level, most existing studies only consider a single event sequence corresponding to one common protagonist. In this paper, we propose a Transformer-based model, called MCPredictor, which integrates deep event-level and script-level information for script event prediction. At the event level, MCPredictor utilizes the rich information in the text to obtain more comprehensive event semantic representations. At the script-level, it considers multiple event sequences corresponding to different participants of the subsequent event. The experimental results on the widely-used New York Times corpus demonstrate the effectiveness and superiority of the proposed model.
Anthology ID:
2021.emnlp-main.777
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9869–9878
Language:
URL:
https://aclanthology.org/2021.emnlp-main.777
DOI:
10.18653/v1/2021.emnlp-main.777
Bibkey:
Cite (ACL):
Long Bai, Saiping Guan, Jiafeng Guo, Zixuan Li, Xiaolong Jin, and Xueqi Cheng. 2021. Integrating Deep Event-Level and Script-Level Information for Script Event Prediction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9869–9878, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Integrating Deep Event-Level and Script-Level Information for Script Event Prediction (Bai et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.777.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.777.mp4
Code
 waltbai/MCPredictor