谷歌浏览器插件
订阅小程序
在清言上使用

Mismatch between Multi-turn Dialogue and its Evaluation Metric in Dialogue State Tracking

PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022): (SHORT PAPERS), VOL 2(2022)

引用 5|浏览53
暂无评分
摘要
Dialogue state tracking (DST) aims to extract essential information from multi-turn dialogue situations and take appropriate actions. A belief state, one of the core pieces of information, refers to the subject and its specific content, and appears in the form of domain-slot-value. The trained model predicts "accumulated" belief states in every turn, and joint goal accuracy and slot accuracy are mainly used to evaluate the prediction; however, we specify that the current evaluation metrics have a critical limitation when evaluating belief states accumulated as the dialogue proceeds, especially in the most used MultiWOZ dataset. Additionally, we propose relative slot accuracy to complement existing metrics. Relative slot accuracy does not depend on the number of predefined slots, and allows intuitive evaluation by assigning relative scores according to the turn of each dialogue. This study also encourages not solely the reporting of joint goal accuracy, but also various complementary metrics in DST tasks for the sake of a realistic evaluation.
更多
查看译文
关键词
dialogue state tracking,evaluation metric,multi-turn
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要