DC Field | Value | Language |
---|---|---|
dc.contributor.author | LEE, GARY GEUNBAE | - |
dc.contributor.author | Lee, Jihyun | - |
dc.contributor.author | Lee, Chaebin | - |
dc.contributor.author | Kim, Yunsu | - |
dc.date.accessioned | 2024-03-06T01:05:16Z | - |
dc.date.available | 2024-03-06T01:05:16Z | - |
dc.date.created | 2024-02-20 | - |
dc.date.issued | 2023-08-20 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/121283 | - |
dc.description.abstract | In task-oriented dialogues, dialogue state tracking (DST) is a critical component as it identifies specific information for the user's purpose. However, as annotating DST data requires a significant amount of human effort, leveraging raw dialogue is crucial. To address this, we propose a new self-training (ST) framework with a verification model. Unlike previous ST methods that rely on extensive hyper-parameter searching to filter out inaccurate data, our verification methodology ensures the accuracy and validity of the dataset without using a fixed threshold. Furthermore, to mitigate overfitting, we augment the dataset by generating diverse user utterances. Even when using only 10% of the labeled data, our approach achieves comparable results to a fully labeled MultiWOZ2.0 dataset. The evaluation of scalability also demonstrates enhanced robustness in predicting unseen values. | - |
dc.language | English | - |
dc.publisher | International Speech Communication Association | - |
dc.relation.isPartOf | 24th International Speech Communication Association, Interspeech 2023 | - |
dc.relation.isPartOf | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH | - |
dc.title | Tracking Must Go On: Dialogue State Tracking with Verified Self-Training | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.identifier.bibliographicCitation | 24th International Speech Communication Association, Interspeech 2023, pp.4678 - 4682 | - |
dc.citation.conferenceDate | 2023-08-20 | - |
dc.citation.conferencePlace | IE | - |
dc.citation.endPage | 4682 | - |
dc.citation.startPage | 4678 | - |
dc.citation.title | 24th International Speech Communication Association, Interspeech 2023 | - |
dc.contributor.affiliatedAuthor | LEE, GARY GEUNBAE | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.