Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313303487> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4313303487 abstract "End-to-end task bots are typically learned over a static and usually limited-size corpus. However, when deployed in dynamic, changing, and open environments to interact with users, task bots tend to fail when confronted with data that deviate from the training corpus, i.e., out-of-distribution samples. In this paper, we study the problem of automatically adapting task bots to changing environments by learning from human-bot interactions with minimum or zero human annotations. We propose SL-AGENT, a novel self-learning framework for building end-to-end task bots. SL-AGENT consists of a dialog model and a pre-trained reward model to predict the quality of an agent response. It enables task bots to automatically adapt to changing environments by learning from the unlabeled human-bot dialog logs accumulated after deployment via reinforcement learning with the incorporated reward model. Experimental results on four well-studied dialog tasks show the effectiveness of SL-AGENT to automatically adapt to changing environments, using both automatic and human evaluations. We will release code and data for further research." @default.
- W4313303487 created "2023-01-06" @default.
- W4313303487 creator A5019458385 @default.
- W4313303487 creator A5047233371 @default.
- W4313303487 creator A5066404470 @default.
- W4313303487 creator A5082213642 @default.
- W4313303487 date "2022-01-18" @default.
- W4313303487 modified "2023-10-14" @default.
- W4313303487 title "Toward Self-learning End-to-End Task-Oriented Dialog Systems" @default.
- W4313303487 doi "https://doi.org/10.48550/arxiv.2201.06849" @default.
- W4313303487 hasPublicationYear "2022" @default.
- W4313303487 type Work @default.
- W4313303487 citedByCount "0" @default.
- W4313303487 crossrefType "posted-content" @default.
- W4313303487 hasAuthorship W4313303487A5019458385 @default.
- W4313303487 hasAuthorship W4313303487A5047233371 @default.
- W4313303487 hasAuthorship W4313303487A5066404470 @default.
- W4313303487 hasAuthorship W4313303487A5082213642 @default.
- W4313303487 hasBestOaLocation W43133034871 @default.
- W4313303487 hasConcept C105339364 @default.
- W4313303487 hasConcept C107457646 @default.
- W4313303487 hasConcept C115903868 @default.
- W4313303487 hasConcept C127413603 @default.
- W4313303487 hasConcept C136764020 @default.
- W4313303487 hasConcept C154945302 @default.
- W4313303487 hasConcept C173853756 @default.
- W4313303487 hasConcept C177264268 @default.
- W4313303487 hasConcept C190954187 @default.
- W4313303487 hasConcept C199360897 @default.
- W4313303487 hasConcept C201995342 @default.
- W4313303487 hasConcept C2776760102 @default.
- W4313303487 hasConcept C2780451532 @default.
- W4313303487 hasConcept C41008148 @default.
- W4313303487 hasConcept C74296488 @default.
- W4313303487 hasConcept C97541855 @default.
- W4313303487 hasConceptScore W4313303487C105339364 @default.
- W4313303487 hasConceptScore W4313303487C107457646 @default.
- W4313303487 hasConceptScore W4313303487C115903868 @default.
- W4313303487 hasConceptScore W4313303487C127413603 @default.
- W4313303487 hasConceptScore W4313303487C136764020 @default.
- W4313303487 hasConceptScore W4313303487C154945302 @default.
- W4313303487 hasConceptScore W4313303487C173853756 @default.
- W4313303487 hasConceptScore W4313303487C177264268 @default.
- W4313303487 hasConceptScore W4313303487C190954187 @default.
- W4313303487 hasConceptScore W4313303487C199360897 @default.
- W4313303487 hasConceptScore W4313303487C201995342 @default.
- W4313303487 hasConceptScore W4313303487C2776760102 @default.
- W4313303487 hasConceptScore W4313303487C2780451532 @default.
- W4313303487 hasConceptScore W4313303487C41008148 @default.
- W4313303487 hasConceptScore W4313303487C74296488 @default.
- W4313303487 hasConceptScore W4313303487C97541855 @default.
- W4313303487 hasLocation W43133034871 @default.
- W4313303487 hasOpenAccess W4313303487 @default.
- W4313303487 hasPrimaryLocation W43133034871 @default.
- W4313303487 hasRelatedWork W1543551553 @default.
- W4313303487 hasRelatedWork W1844013633 @default.
- W4313303487 hasRelatedWork W2412715517 @default.
- W4313303487 hasRelatedWork W2603292746 @default.
- W4313303487 hasRelatedWork W2774891019 @default.
- W4313303487 hasRelatedWork W3074656709 @default.
- W4313303487 hasRelatedWork W3088238433 @default.
- W4313303487 hasRelatedWork W3200996968 @default.
- W4313303487 hasRelatedWork W4225852895 @default.
- W4313303487 hasRelatedWork W4299854802 @default.
- W4313303487 isParatext "false" @default.
- W4313303487 isRetracted "false" @default.
- W4313303487 workType "article" @default.