dc.citation.conferencePlace |
US |
- |
dc.citation.conferencePlace |
New Orleans |
- |
dc.citation.title |
International Conference on Learning Representations |
- |
dc.contributor.author |
Lee, Sang-Woo |
- |
dc.contributor.author |
Gao, Tong |
- |
dc.contributor.author |
Yang, Sohee |
- |
dc.contributor.author |
Yoo, Jaejun |
- |
dc.contributor.author |
Ha, Jung-Woo |
- |
dc.date.accessioned |
2024-02-01T00:35:59Z |
- |
dc.date.available |
2024-02-01T00:35:59Z |
- |
dc.date.created |
2021-08-19 |
- |
dc.date.issued |
2019-05 |
- |
dc.description.abstract |
Answerer in Questioner's Mind (AQM) is an information-theoretic framework that has been recently proposed for task-oriented dialog systems. AQM benefits from asking a question that would maximize the information gain when it is asked. However, due to its intrinsic nature of explicitly calculating the information gain, AQM has a limitation when the solution space is very large. To address this, we propose AQM+ that can deal with a large-scale problem and ask a question that is more coherent to the current context of the dialog. We evaluate our method on GuessWhich, a challenging task-oriented visual dialog problem, where the number of candidate classes is near 10K. Our experimental results and ablation studies show that AQM+ outperforms the state-of-the-art models by a remarkable margin with a reasonable approximation. In particular, the proposed AQM+ reduces more than 60% of error as the dialog proceeds, while the comparative algorithms diminish the error by less than 6%. Based on our results, we argue that AQM+ is a general task-oriented dialog algorithm that can be applied for non-yes-or-no responses. |
- |
dc.identifier.bibliographicCitation |
International Conference on Learning Representations |
- |
dc.identifier.issn |
0000-0000 |
- |
dc.identifier.scopusid |
2-s2.0-85083953159 |
- |
dc.identifier.uri |
https://scholarworks.unist.ac.kr/handle/201301/79877 |
- |
dc.language |
영어 |
- |
dc.publisher |
International Conference on Learning Representations |
- |
dc.title |
Large-scale answerer in questioner's mind for visual dialog question generation |
- |
dc.type |
Conference Paper |
- |
dc.date.conferenceDate |
2019-05-06 |
- |