Joint Overlapping Event Extraction Model via Role Pre-Judgment with Trigger and Context Embeddings
The objective of event extraction is to recognize event triggers and event categories within unstructured text and produce structured event arguments. However, there is a common phenomenon of triggers and arguments of different event types in a sentence that may be the same word elements, which pose...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/22/4688 |
_version_ | 1797459443239092224 |
---|---|
author | Qian Chen Kehan Yang Xin Guo Suge Wang Jian Liao Jianxing Zheng |
author_facet | Qian Chen Kehan Yang Xin Guo Suge Wang Jian Liao Jianxing Zheng |
author_sort | Qian Chen |
collection | DOAJ |
description | The objective of event extraction is to recognize event triggers and event categories within unstructured text and produce structured event arguments. However, there is a common phenomenon of triggers and arguments of different event types in a sentence that may be the same word elements, which poses new challenges to this task. In this article, a joint learning framework for overlapping event extraction (ROPEE) is proposed. In this framework, a role pre-judgment module is devised prior to argument extraction. It conducts role pre-judgment by leveraging the correlation between event types and roles, as well as trigger embeddings. Experiments on the FewFC show that the proposed model outperforms other baseline models in terms of Trigger Classification, Argument Identification, and Argument Classification by 0.4%, 0.9%, and 0.6%. In scenarios of trigger overlap and argument overlap, the proposed model outperforms the baseline models in terms of Argument Identification and Argument Classification by 0.9%, 1.2%, 0.7%, and 0.6%, respectively, indicating the effectiveness of ROPEE in solving overlapping events. |
first_indexed | 2024-03-09T16:51:24Z |
format | Article |
id | doaj.art-0734587dde8c451a920acafb4dbe307d |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-09T16:51:24Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-0734587dde8c451a920acafb4dbe307d2023-11-24T14:39:44ZengMDPI AGElectronics2079-92922023-11-011222468810.3390/electronics12224688Joint Overlapping Event Extraction Model via Role Pre-Judgment with Trigger and Context EmbeddingsQian Chen0Kehan Yang1Xin Guo2Suge Wang3Jian Liao4Jianxing Zheng5School of Computer and Information Technology, Shanxi University, Taiyuan 030006, ChinaSchool of Computer and Information Technology, Shanxi University, Taiyuan 030006, ChinaSchool of Computer and Information Technology, Shanxi University, Taiyuan 030006, ChinaSchool of Computer and Information Technology, Shanxi University, Taiyuan 030006, ChinaSchool of Computer and Information Technology, Shanxi University, Taiyuan 030006, ChinaSchool of Computer and Information Technology, Shanxi University, Taiyuan 030006, ChinaThe objective of event extraction is to recognize event triggers and event categories within unstructured text and produce structured event arguments. However, there is a common phenomenon of triggers and arguments of different event types in a sentence that may be the same word elements, which poses new challenges to this task. In this article, a joint learning framework for overlapping event extraction (ROPEE) is proposed. In this framework, a role pre-judgment module is devised prior to argument extraction. It conducts role pre-judgment by leveraging the correlation between event types and roles, as well as trigger embeddings. Experiments on the FewFC show that the proposed model outperforms other baseline models in terms of Trigger Classification, Argument Identification, and Argument Classification by 0.4%, 0.9%, and 0.6%. In scenarios of trigger overlap and argument overlap, the proposed model outperforms the baseline models in terms of Argument Identification and Argument Classification by 0.9%, 1.2%, 0.7%, and 0.6%, respectively, indicating the effectiveness of ROPEE in solving overlapping events.https://www.mdpi.com/2079-9292/12/22/4688overlapping event extractiontrigger overlapargument overlapjoint learningrole pre-judgment |
spellingShingle | Qian Chen Kehan Yang Xin Guo Suge Wang Jian Liao Jianxing Zheng Joint Overlapping Event Extraction Model via Role Pre-Judgment with Trigger and Context Embeddings Electronics overlapping event extraction trigger overlap argument overlap joint learning role pre-judgment |
title | Joint Overlapping Event Extraction Model via Role Pre-Judgment with Trigger and Context Embeddings |
title_full | Joint Overlapping Event Extraction Model via Role Pre-Judgment with Trigger and Context Embeddings |
title_fullStr | Joint Overlapping Event Extraction Model via Role Pre-Judgment with Trigger and Context Embeddings |
title_full_unstemmed | Joint Overlapping Event Extraction Model via Role Pre-Judgment with Trigger and Context Embeddings |
title_short | Joint Overlapping Event Extraction Model via Role Pre-Judgment with Trigger and Context Embeddings |
title_sort | joint overlapping event extraction model via role pre judgment with trigger and context embeddings |
topic | overlapping event extraction trigger overlap argument overlap joint learning role pre-judgment |
url | https://www.mdpi.com/2079-9292/12/22/4688 |
work_keys_str_mv | AT qianchen jointoverlappingeventextractionmodelviaroleprejudgmentwithtriggerandcontextembeddings AT kehanyang jointoverlappingeventextractionmodelviaroleprejudgmentwithtriggerandcontextembeddings AT xinguo jointoverlappingeventextractionmodelviaroleprejudgmentwithtriggerandcontextembeddings AT sugewang jointoverlappingeventextractionmodelviaroleprejudgmentwithtriggerandcontextembeddings AT jianliao jointoverlappingeventextractionmodelviaroleprejudgmentwithtriggerandcontextembeddings AT jianxingzheng jointoverlappingeventextractionmodelviaroleprejudgmentwithtriggerandcontextembeddings |