Learning to Build Reasoning Chains by Reliable Path Retrieval
文献类型:会议论文
作者 | Zhu MJ(朱敏郡); Weng YX(翁诣轩); He SZ(何世柱); Liu K(刘康); Zhao J(赵军) |
出版日期 | 2023 |
会议日期 | 2023 |
会议地点 | 希腊罗德岛 |
英文摘要 | Question answering (QA) systems have long pursued the ability to reason over explicit knowledge credibly. Recent work has incorporated knowledge into fine-grained sentences and constructed natural language database (NLDB) task, and conducts complex QA with explicit reasoning chains. Existing models focus on retrieving evidence by combining multiple modules or discretely. However, these models ignore utilizing path information (e.g. sentence order), which is proven to be important for evidence retrievers. In this work, we propose a ReliAble Path-retrieval (RAP) to generate varying length evidence chains iteratively. It comprehensively models reasoning chains and introduces loss from two views. The experimental results show that our model demonstrates state-of-the-art performance on both evidence chain retrieval and question-answering tasks. Additional experiments on sequential supervised and sequential unsupervised retrieval fully indicate the significance of RAP. |
会议录出版者 | IEEE |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/52281] |
专题 | 模式识别国家重点实验室_自然语言处理 |
通讯作者 | Zhao J(赵军) |
作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhu MJ,Weng YX,He SZ,et al. Learning to Build Reasoning Chains by Reliable Path Retrieval[C]. 见:. 希腊罗德岛. 2023. |
入库方式: OAI收割
来源:自动化研究所
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。