A contrastive learning framework for event detection via semantic type prototype representation modelling
The diversity of natural language expressions for describing events poses a challenge for the task of Event Detection (ED) with machine learning methods. To detect and classify event mentions, ED models essentially need to construct a semantic linkage between representations of the mentions and a se...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/171254 |
| _version_ | 1826127583298715648 |
|---|---|
| author | Hao, Anran Luu, Anh Tuan Hui, Siu Cheung Su, Jian |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Hao, Anran Luu, Anh Tuan Hui, Siu Cheung Su, Jian |
| author_sort | Hao, Anran |
| collection | NTU |
| description | The diversity of natural language expressions for describing events poses a challenge for the task of Event Detection (ED) with machine learning methods. To detect and classify event mentions, ED models essentially need to construct a semantic linkage between representations of the mentions and a set of target types. Unfortunately, most existing models use meaningless homogeneous one-hot vectors to represent the event type classes in ED, ignoring the fact that the event type labels also consist of meaningful words and can provide important clues for type representation learning. In this paper, we propose a Contrastive Semantic Prototype Representation Learning Framework for Event Detection (SemPRE), which exploits the pre-defined event type label words to inject the semantic information of the types and guide event detection. Specifically, we utilize pre-trained BERT to fuse text and event type into a joint representation space, and employ a contrastive-regularized module to enhance cross-type interaction. We conduct extensive experiments on the ACE 2005 and MAVEN benchmark datasets. The performance results show that our proposed SemPRE model achieves state-of-the-art performance on the datasets and outperforms existing baselines on limited annotated data and without using any external resources. Further analysis shows that our model is also effective in detecting multiple events and ambiguous trigger words. |
| first_indexed | 2024-10-01T07:11:15Z |
| format | Journal Article |
| id | ntu-10356/171254 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:11:15Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1712542023-10-18T01:25:51Z A contrastive learning framework for event detection via semantic type prototype representation modelling Hao, Anran Luu, Anh Tuan Hui, Siu Cheung Su, Jian School of Computer Science and Engineering Institute for Infocomm Research, A*STAR Engineering::Computer science and engineering Event Detection Information Extraction The diversity of natural language expressions for describing events poses a challenge for the task of Event Detection (ED) with machine learning methods. To detect and classify event mentions, ED models essentially need to construct a semantic linkage between representations of the mentions and a set of target types. Unfortunately, most existing models use meaningless homogeneous one-hot vectors to represent the event type classes in ED, ignoring the fact that the event type labels also consist of meaningful words and can provide important clues for type representation learning. In this paper, we propose a Contrastive Semantic Prototype Representation Learning Framework for Event Detection (SemPRE), which exploits the pre-defined event type label words to inject the semantic information of the types and guide event detection. Specifically, we utilize pre-trained BERT to fuse text and event type into a joint representation space, and employ a contrastive-regularized module to enhance cross-type interaction. We conduct extensive experiments on the ACE 2005 and MAVEN benchmark datasets. The performance results show that our proposed SemPRE model achieves state-of-the-art performance on the datasets and outperforms existing baselines on limited annotated data and without using any external resources. Further analysis shows that our model is also effective in detecting multiple events and ambiguous trigger words. This research is supported by the Agency for Science, Technology, and Research (A*STAR), Singapore. 2023-10-18T01:25:51Z 2023-10-18T01:25:51Z 2023 Journal Article Hao, A., Luu, A. T., Hui, S. C. & Su, J. (2023). A contrastive learning framework for event detection via semantic type prototype representation modelling. Neurocomputing, 556, 126613-. https://dx.doi.org/10.1016/j.neucom.2023.126613 0925-2312 https://hdl.handle.net/10356/171254 10.1016/j.neucom.2023.126613 2-s2.0-85168084209 556 126613 en Neurocomputing © 2023 Elsevier B.V. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Event Detection Information Extraction Hao, Anran Luu, Anh Tuan Hui, Siu Cheung Su, Jian A contrastive learning framework for event detection via semantic type prototype representation modelling |
| title | A contrastive learning framework for event detection via semantic type prototype representation modelling |
| title_full | A contrastive learning framework for event detection via semantic type prototype representation modelling |
| title_fullStr | A contrastive learning framework for event detection via semantic type prototype representation modelling |
| title_full_unstemmed | A contrastive learning framework for event detection via semantic type prototype representation modelling |
| title_short | A contrastive learning framework for event detection via semantic type prototype representation modelling |
| title_sort | contrastive learning framework for event detection via semantic type prototype representation modelling |
| topic | Engineering::Computer science and engineering Event Detection Information Extraction |
| url | https://hdl.handle.net/10356/171254 |
| work_keys_str_mv | AT haoanran acontrastivelearningframeworkforeventdetectionviasemantictypeprototyperepresentationmodelling AT luuanhtuan acontrastivelearningframeworkforeventdetectionviasemantictypeprototyperepresentationmodelling AT huisiucheung acontrastivelearningframeworkforeventdetectionviasemantictypeprototyperepresentationmodelling AT sujian acontrastivelearningframeworkforeventdetectionviasemantictypeprototyperepresentationmodelling AT haoanran contrastivelearningframeworkforeventdetectionviasemantictypeprototyperepresentationmodelling AT luuanhtuan contrastivelearningframeworkforeventdetectionviasemantictypeprototyperepresentationmodelling AT huisiucheung contrastivelearningframeworkforeventdetectionviasemantictypeprototyperepresentationmodelling AT sujian contrastivelearningframeworkforeventdetectionviasemantictypeprototyperepresentationmodelling |