Dialogue state tracking with incremental reasoning
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 g...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Institutional Knowledge at Singapore Management University
2021
|
| Subjects: | |
| Online Access: | https://ink.library.smu.edu.sg/sis_research/7577 https://ink.library.smu.edu.sg/context/sis_research/article/8580/viewcontent/tacl_a_00384.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Singapore Management University |
| Language: | English |
| Summary: | 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-theart methods in terms of joint belief accuracy for MultiWOZ 2.1, a large-scale human–human dialogue dataset across multiple domains. |
|---|