Publications
Detailed Information
Answerer in questioner's mind: Information theoretic approach to goal-oriented visual dialog
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Sang-Woo | - |
dc.contributor.author | Heo, Yu-Jung | - |
dc.contributor.author | Zhang, Byoung-Tak | - |
dc.date.accessioned | 2022-05-04T01:43:07Z | - |
dc.date.available | 2022-05-04T01:43:07Z | - |
dc.date.created | 2021-01-27 | - |
dc.date.issued | 2018-01 | - |
dc.identifier.citation | Advances in Neural Information Processing Systems, Vol.2018-December, pp.2579-2589 | - |
dc.identifier.issn | 1049-5258 | - |
dc.identifier.uri | https://hdl.handle.net/10371/179344 | - |
dc.description.abstract | © 2018 Curran Associates Inc.All rights reserved.Goal-oriented dialog has been given attention due to its numerous applications in artificial intelligence. Goal-oriented dialogue tasks occur when a questioner asks an action-oriented question and an answerer responds with the intent of letting the questioner know a correct action to take. To ask the adequate question, deep learning and reinforcement learning have been recently applied. However, these approaches struggle to find a competent recurrent neural questioner, owing to the complexity of learning a series of sentences. Motivated by theory of mind, we propose Answerer in Questioner's Mind (AQM), a novel information theoretic algorithm for goal-oriented dialog. With AQM, a questioner asks and infers based on an approximated probabilistic model of the answerer. The questioner figures out the answerer's intention via selecting a plausible question by explicitly calculating the information gain of the candidate intentions and possible answers to each question. We test our framework on two goal-oriented visual dialog tasks: MNIST Counting Dialog and GuessWhat?!. In our experiments, AQM outperforms comparative algorithms by a large margin. | - |
dc.language | 영어 | - |
dc.publisher | Neural information processing systems foundation | - |
dc.title | Answerer in questioner's mind: Information theoretic approach to goal-oriented visual dialog | - |
dc.type | Article | - |
dc.citation.journaltitle | Advances in Neural Information Processing Systems | - |
dc.identifier.scopusid | 2-s2.0-85064814561 | - |
dc.citation.endpage | 2589 | - |
dc.citation.startpage | 2579 | - |
dc.citation.volume | 2018-December | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Zhang, Byoung-Tak | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.