中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 学术期刊
  5. International Journal of Automation and Computing
GraphFlow+: Exploiting Conversation Flow in Conversational Machine Comprehension with Graph Neural Networks

文献类型：期刊论文

作者Jing Hu2; Lingfei Wu3; Yu Chen1; Po Hu2; Mohammed J. Zaki4
刊名Machine Intelligence Research
出版日期2024
卷号21期号:2页码:272-282
关键词Conversational machine comprehension (MC), reading comprehension, question answering, graph neural networks (GNNs), natural language processing (NLP)
ISSN号2731-538X
DOI10.1007/s11633-023-1421-0
英文摘要The conversation machine comprehension (MC) task aims to answer questions in the multi-turn conversation for a single passage. However, recent approaches don′t exploit information from historical conversations effectively, which results in some references and ellipsis in the current question cannot be recognized. In addition, these methods do not consider the rich semantic relationships between words when reasoning about the passage text. In this paper, we propose a novel model GraphFlow+, which constructs a context graph for each conversation turn and uses a unique recurrent graph neural network (GNN) to model the temporal dependencies between the context graphs of each turn. Specifically, we exploit three different ways to construct text graphs, including the dynamic graph, static graph, and hybrid graph that combines the two. Our experiments on CoQA, QuAC and DoQA show that the GraphFlow+ model can outperform the state-of-the-art approaches.
源URL[http://ir.ia.ac.cn/handle/173211/56038]  
专题自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位1.Meta, Mountain View 94039, USA
2.School of Computer Science, Central China Normal University, Wuhan 430079, China
3.Pinterest, San Francisco 94016, USA
4.Rensselaer Polytechnic Institute, Troy 12180, USA
推荐引用方式
GB/T 7714		 Jing Hu,Lingfei Wu,Yu Chen,et al. GraphFlow+: Exploiting Conversation Flow in Conversational Machine Comprehension with Graph Neural Networks[J]. Machine Intelligence Research,2024,21(2):272-282.
APA Jing Hu,Lingfei Wu,Yu Chen,Po Hu,&Mohammed J. Zaki.(2024).GraphFlow+: Exploiting Conversation Flow in Conversational Machine Comprehension with Graph Neural Networks.Machine Intelligence Research,21(2),272-282.
MLA Jing Hu,et al."GraphFlow+: Exploiting Conversation Flow in Conversational Machine Comprehension with Graph Neural Networks".Machine Intelligence Research 21.2(2024):272-282.

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。