.png){kind=icon}
返回
Dialogue State Tracking with Incremental Reasoning
.png){kind=icon}
OA
AI
DOI：10.1162/tacl_a_00384.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined slot-value pairs, or generating values for different slots given the dialogue history. Both have limitations on considering dependencies that occur on dialogues, and are lacking of reasoning capabilities. This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data. Empirical results demonstrate that our method outperforms the state-of-the-art methods in terms of joint belief accuracy for MultiWOZ 2.1, a large-scale human-human dialogue dataset across multiple domains.
期刊
T
IF:
6.9
论文数:
486
被引数:
5.7K
机构
引用论文
.png){kind=icon}
Bayesian update of dialogue state: A POMDP framework for spoken dialogue systems对话状态的贝叶斯更新: 口语对话系统的POMDP框架
OAAI
OAAI分享收藏 没有更多内容
没有更多内容