Learning Entangled Interactions of Complex Causality via Self-Paced Contrastive Learning
文献类型：期刊论文
| 作者 | Liang, Yunji1; Liu, Lei1; Huangfu, Luwen2; Samtani, Sagar3; Yu, Zhiwen1; Daniel D Zeng4
|
| 刊名 | ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
 |
| 出版日期 | 2024-04-01 |
| 卷号 | 18期号:3页码:24 |
| 关键词 | Entangled interaction causality detection complex causality self-paced contrastive learning causal directionality |
| ISSN号 | 1556-4681 |
| DOI | 10.1145/3632406 |
| 通讯作者 | Liang, Yunji(liangyunji@nwpu.edu.cn) ; Huangfu, Luwen(lhuangfu@sdsu.edu) |
| 英文摘要 | Learning causality from large-scale text corpora is an important task with numerous applications-for example, in finance, biology, medicine, and scientific discovery. Prior studies have focused mainly on simple causality, which only includes one cause-effect pair. However, causality is notoriously difficult to understand and analyze because of multiple cause spans and their entangled interactions. To detect complex causality, we propose a self-paced contrastive learning model, namely N2NCause, to learn entangled interactions between multiple spans. Specifically, N2NCause introduces data enhancement operations to convert implicit expressions into explicit expressions with the most rational causal connectives for the synthesis of positive samples and to invert the directed connection between a cause-effect pair for the synthesis of negative samples. To learn the semantic dependency and causal direction of positive and negative samples, self-paced contrastive learning is proposed to learn the entangled interactions among spans, including the interaction direction and interaction field. We evaluated the performance of N2NCause in three cause-effect detection tasks. The experimental results show that, with the least data annotation efforts, N2NCause demonstrates competitive performance in detecting simple cause-effect relations, and it is superior to existing solutions for the detection of complex causality. |
| WOS关键词 | RELATION EXTRACTION ; CORPUS |
| 资助项目 | Natural Science Foundation of China[62372378] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001168400500009 |
| 出版者 | ASSOC COMPUTING MACHINERY |
| 资助机构 | Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57851]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Liang, Yunji; Huangfu, Luwen |
| 作者单位 | 1.Northwestern Polytech Univ, Sch Comp Sci, 1 Dongxiang Rd, Xian 710129, Shaanxi, Peoples R China 2.San Diego State Univ, Fowler Coll Business, 5500 Campanile Dr, San Diego, CA 92182 USA 3.Indiana Univ, Kelley Sch Business, 107 S Indiana Ave, Bloomington, IN 47405 USA 4.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liang, Yunji,Liu, Lei,Huangfu, Luwen,et al. Learning Entangled Interactions of Complex Causality via Self-Paced Contrastive Learning[J]. ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA,2024,18(3):24. |
| APA | Liang, Yunji,Liu, Lei,Huangfu, Luwen,Samtani, Sagar,Yu, Zhiwen,&Daniel D Zeng.(2024).Learning Entangled Interactions of Complex Causality via Self-Paced Contrastive Learning.ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA,18(3),24. |
| MLA | Liang, Yunji,et al."Learning Entangled Interactions of Complex Causality via Self-Paced Contrastive Learning".ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 18.3(2024):24. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。