Quantum Probability-inspired Graph Attention Network for Modeling Complex Text Interaction
文献类型：期刊论文
| ; | |
| 作者 | Yan, Peng1,2 ; Li, Linjing1,2,3; Zeng, Daniel1,2,3
|
| 刊名 | KNOWLEDGE-BASED SYSTEMS
 ; KNOWLEDGE-BASED SYSTEMS
|
| 出版日期 | 2021-12-25 ; 2021-12-25 |
| 卷号 | 234页码:12 |
| 关键词 | Natural language processing Natural language processing Quantum probability Graph attention network Quantum probability Graph attention network |
| ISSN号 | 0950-7051 ; 0950-7051 |
| DOI | 10.1016/j.knosys.2021.107557 ; 10.1016/j.knosys.2021.107557 |
| 通讯作者 | Li, Linjing(linjing.li@ia.ac.cn) ; Li, Linjing(linjing.li@ia.ac.cn) |
| 英文摘要 | Inspired by quantum-like phenomena in human language understanding, recent studies propose quan-tum probability-inspired neural networks to model natural language by treating words as superposition states and a sentence as a mixed state. However, many complex natural language processing tasks (e.g., emotion-cause pair extraction or joint dialog act recognition and sentiment classification) require modeling the complex and graphical interaction of multiple text pieces (e.g., multiple clauses in a document or multiple utterances in a dialog). The existing quantum probability-inspired neural networks only encode sequential interaction of a sequence of words, but cannot model the complex interaction of text pieces. To generalize the quantum framework from modeling word sequence to modeling complex and graphical text interaction, we propose a Quantum Probability-inspired Graph Attention NeTwork (QPGAT) by combining quantum probability and graph attention mechanism in a unified framework. Specifically, a text interaction graph is firstly constructed to describe the complex interaction of text pieces. Then QPGAT models each text node as a particle in a superposition state and each node's neighborhood in the graph as a mixed system in a mixed state to learn interaction-aware text node representations. We apply QPGAT to the two important and complex NLP tasks, emotion- cause pair extraction and joint dialog act recognition and sentiment classification. Experiment results show that QPGAT is competitive compared with the state-of-the-art methods on the two complex NLP tasks, demonstrating the effectiveness of QPGAT. Moreover, QPGAT can also provide a reasonable post-hoc explanation about the model decision process for emotion-cause pair extraction. (c) 2021 Elsevier B.V. All rights reserved.; Inspired by quantum-like phenomena in human language understanding, recent studies propose quan-tum probability-inspired neural networks to model natural language by treating words as superposition states and a sentence as a mixed state. However, many complex natural language processing tasks (e.g., emotion-cause pair extraction or joint dialog act recognition and sentiment classification) require modeling the complex and graphical interaction of multiple text pieces (e.g., multiple clauses in a document or multiple utterances in a dialog). The existing quantum probability-inspired neural networks only encode sequential interaction of a sequence of words, but cannot model the complex interaction of text pieces. To generalize the quantum framework from modeling word sequence to modeling complex and graphical text interaction, we propose a Quantum Probability-inspired Graph Attention NeTwork (QPGAT) by combining quantum probability and graph attention mechanism in a unified framework. Specifically, a text interaction graph is firstly constructed to describe the complex interaction of text pieces. Then QPGAT models each text node as a particle in a superposition state and each node's neighborhood in the graph as a mixed system in a mixed state to learn interaction-aware text node representations. We apply QPGAT to the two important and complex NLP tasks, emotion- cause pair extraction and joint dialog act recognition and sentiment classification. Experiment results show that QPGAT is competitive compared with the state-of-the-art methods on the two complex NLP tasks, demonstrating the effectiveness of QPGAT. Moreover, QPGAT can also provide a reasonable post-hoc explanation about the model decision process for emotion-cause pair extraction. (c) 2021 Elsevier B.V. All rights reserved. |
| WOS研究方向 | Computer Science ; Computer Science |
| 语种 | 英语 ; 英语 |
| WOS记录号 | WOS:000709963300005 ; WOS:000709963300005 |
| 出版者 | ELSEVIER ; ELSEVIER |
| 源URL | [http://ir.ia.ac.cn/handle/173211/46279]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_互联网大数据与安全信息学研究中心 |
| 通讯作者 | Li, Linjing |
| 作者单位 | 1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Shenzhen Artificial Intelligence & Data Sci Inst, Shenzhen, Peoples R China |
| 推荐引用方式 GB/T 7714 | Yan, Peng,Li, Linjing,Zeng, Daniel. Quantum Probability-inspired Graph Attention Network for Modeling Complex Text Interaction, Quantum Probability-inspired Graph Attention Network for Modeling Complex Text Interaction[J]. KNOWLEDGE-BASED SYSTEMS, KNOWLEDGE-BASED SYSTEMS,2021, 2021,234, 234:12, 12. |
| APA | Yan, Peng,Li, Linjing,&Zeng, Daniel.(2021).Quantum Probability-inspired Graph Attention Network for Modeling Complex Text Interaction.KNOWLEDGE-BASED SYSTEMS,234,12. |
| MLA | Yan, Peng,et al."Quantum Probability-inspired Graph Attention Network for Modeling Complex Text Interaction".KNOWLEDGE-BASED SYSTEMS 234(2021):12. |
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。