Abstract
“针对现有中文因果关系抽取方法对因果事件边界难以识别和文本特征表示不充分的问题,提出了一种基于外部词汇信息和注意力机制的中文因果关系抽取模型BiLSTM-TWAM+CRF。该模型首次使用SoftLexicon方法引入外部词汇信息构建词集,解决了因果事件边界难以识别的问题。通过构建的双路关注模块TWAM(Two Way Attention Module),实现了从局部和全局两个角度充分刻画文本特征。实验结果表明,与当前中文因果关系抽取模型相比较,本文方法表现出更优的抽取效果。”- Anthology ID:
- 2022.ccl-1.18
- Volume:
- Proceedings of the 21st Chinese National Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Nanchang, China
- Editors:
- Maosong Sun (孙茂松), Yang Liu (刘洋), Wanxiang Che (车万翔), Yang Feng (冯洋), Xipeng Qiu (邱锡鹏), Gaoqi Rao (饶高琦), Yubo Chen (陈玉博)
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 190–200
- Language:
- Chinese
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2022.ccl-1.18/
- DOI:
- Cite (ACL):
- Shilin Cui and Rong Yan. 2022. 基于SoftLexicon和注意力机制的中文因果关系抽取(Chinese Causality Extraction Based on SoftLexicon and Attention Mechanism). In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 190–200, Nanchang, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 基于SoftLexicon和注意力机制的中文因果关系抽取(Chinese Causality Extraction Based on SoftLexicon and Attention Mechanism) (Cui & Yan, CCL 2022)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2022.ccl-1.18.pdf