Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289672286> ?p ?o ?g. }
Showing items 1 to 37 of
37
with 100 items per page.
- W4289672286 abstract "In a dialog, there can be multiple valid next utterances at any point. The present end-to-end neural methods for dialog do not take this into account. They learn with the assumption that at any time there is only one correct next utterance. In this work, we focus on this problem in the goal-oriented dialog setting where there are different paths to reach a goal. We propose a new method, that uses a combination of supervised learning and reinforcement learning approaches to address this issue. We also propose a new and more effective testbed, permuted-bAbI dialog tasks, by introducing multiple valid next utterances to the original-bAbI dialog tasks, which allows evaluation of goal-oriented dialog systems in a more realistic setting. We show that there is a significant drop in performance of existing end-to-end neural methods from 81.5% per-dialog accuracy on original-bAbI dialog tasks to 30.3% on permuted-bAbI dialog tasks. We also show that our proposed method improves the performance and achieves 47.3% per-dialog accuracy on permuted-bAbI dialog tasks." @default.
- W4289672286 created "2022-08-04" @default.
- W4289672286 creator A5022597629 @default.
- W4289672286 creator A5037281393 @default.
- W4289672286 creator A5065366930 @default.
- W4289672286 creator A5091341927 @default.
- W4289672286 date "2018-08-24" @default.
- W4289672286 modified "2023-09-30" @default.
- W4289672286 title "Learning End-to-End Goal-Oriented Dialog with Multiple Answers" @default.
- W4289672286 doi "https://doi.org/10.48550/arxiv.1808.09996" @default.
- W4289672286 hasPublicationYear "2018" @default.
- W4289672286 type Work @default.
- W4289672286 citedByCount "0" @default.
- W4289672286 crossrefType "posted-content" @default.
- W4289672286 hasAuthorship W4289672286A5022597629 @default.
- W4289672286 hasAuthorship W4289672286A5037281393 @default.
- W4289672286 hasAuthorship W4289672286A5065366930 @default.
- W4289672286 hasAuthorship W4289672286A5091341927 @default.
- W4289672286 hasBestOaLocation W42896722861 @default.
- W4289672286 hasConcept C136764020 @default.
- W4289672286 hasConcept C154945302 @default.
- W4289672286 hasConcept C15744967 @default.
- W4289672286 hasConcept C173853756 @default.
- W4289672286 hasConcept C41008148 @default.
- W4289672286 hasConcept C74296488 @default.
- W4289672286 hasConceptScore W4289672286C136764020 @default.
- W4289672286 hasConceptScore W4289672286C154945302 @default.
- W4289672286 hasConceptScore W4289672286C15744967 @default.
- W4289672286 hasConceptScore W4289672286C173853756 @default.
- W4289672286 hasConceptScore W4289672286C41008148 @default.
- W4289672286 hasConceptScore W4289672286C74296488 @default.
- W4289672286 hasLocation W42896722861 @default.
- W4289672286 hasOpenAccess W4289672286 @default.
- W4289672286 hasPrimaryLocation W42896722861 @default.
- W4289672286 isParatext "false" @default.
- W4289672286 isRetracted "false" @default.
- W4289672286 workType "article" @default.