Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
7-2022
Abstract
Prediction over event sequences is critical for many real-world applications in Information Retrieval and Natural Language Processing. Future Event Generation (FEG) is a challenging task in event sequence prediction because it requires not only fluent text generation but also commonsense reasoning to maintain the logical coherence of the entire event story. In this paper, we propose a novel explainable FEG framework, Coep. It highlights and integrates two types of event knowledge, sequential knowledge of direct event-event relations and inferential knowledge that reflects the intermediate character psychology between events, such as intents, causes, reactions, which intrinsically pushes the story forward. To alleviate the knowledge forgetting issue, we design two modules, IM and GM, for each type of knowledge, which are combined via prompt tuning. First, IM focuses on understanding inferential knowledge to generate commonsense explanations and provide a soft prompt vector for GM. We also design a contrastive discriminator for better generalization ability. Second, GM generates future events by modeling direct sequential knowledge with the guidance of IM. Automatic and human evaluation demonstrate that our approach can generate more coherent, specific, and logical future events.
Keywords
commonsense reasoning, contrastive training, textual event generation
Discipline
Artificial Intelligence and Robotics | Databases and Information Systems
Research Areas
Intelligent Systems and Optimization
Publication
SIGIR '22: Proceedings of the 45th ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, July 11-15
First Page
1098
Last Page
1109
ISBN
9781450387323
Identifier
10.1145/3477495.3532080
Publisher
ACM
City or Country
New York
Citation
LIN, Li; CAO, Yixin; HUANG, Lifu; LI, Shu Ang; HU, Xuming; WEN, Lijie; and WANG, Jianmin.
What makes the story forward?: Inferring commonsense explanations as prompts for future event generation. (2022). SIGIR '22: Proceedings of the 45th ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, July 11-15. 1098-1109.
Available at: https://ink.library.smu.edu.sg/sis_research/7229
Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.
Additional URL
https://doi.org/10.1145/3477495.3532080