Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319986212> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4319986212 abstract "An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current approaches improved the response quality, but they over-look the training signals present in the dialogue data. We can leverage these signals to generate the weakly supervised training data for learning dialog policy and reward estimator, and make the policy take actions (generates responses) which can foresee the future direction for a successful (rewarding) conversation. We simulate the dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other. The agent uses dynamic blocking to generate ranked diverse responses and exploration-exploitation to select among the Top-K responses. Each simulated state-action pair is evaluated (works as a weak annotation) with three quality modules: Semantic Relevant, Semantic Coherence and Consistent Flow. Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation on both automatic evaluation and human judgement." @default.
- W4319986212 created "2023-02-11" @default.
- W4319986212 creator A5002245577 @default.
- W4319986212 date "2021-08-01" @default.
- W4319986212 modified "2023-10-17" @default.
- W4319986212 title "WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue" @default.
- W4319986212 doi "https://doi.org/10.48550/arxiv.2108.01487" @default.
- W4319986212 hasPublicationYear "2021" @default.
- W4319986212 type Work @default.
- W4319986212 citedByCount "0" @default.
- W4319986212 crossrefType "posted-content" @default.
- W4319986212 hasAuthorship W4319986212A5002245577 @default.
- W4319986212 hasBestOaLocation W43199862121 @default.
- W4319986212 hasConcept C105795698 @default.
- W4319986212 hasConcept C111472728 @default.
- W4319986212 hasConcept C119857082 @default.
- W4319986212 hasConcept C121332964 @default.
- W4319986212 hasConcept C136389625 @default.
- W4319986212 hasConcept C136764020 @default.
- W4319986212 hasConcept C138885662 @default.
- W4319986212 hasConcept C153083717 @default.
- W4319986212 hasConcept C154945302 @default.
- W4319986212 hasConcept C15744967 @default.
- W4319986212 hasConcept C173853756 @default.
- W4319986212 hasConcept C174348530 @default.
- W4319986212 hasConcept C17744445 @default.
- W4319986212 hasConcept C185429906 @default.
- W4319986212 hasConcept C199539241 @default.
- W4319986212 hasConcept C2776321320 @default.
- W4319986212 hasConcept C2776548248 @default.
- W4319986212 hasConcept C2777200299 @default.
- W4319986212 hasConcept C2779530757 @default.
- W4319986212 hasConcept C2781181686 @default.
- W4319986212 hasConcept C31258907 @default.
- W4319986212 hasConcept C33923547 @default.
- W4319986212 hasConcept C41008148 @default.
- W4319986212 hasConcept C46312422 @default.
- W4319986212 hasConcept C50644808 @default.
- W4319986212 hasConcept C62520636 @default.
- W4319986212 hasConceptScore W4319986212C105795698 @default.
- W4319986212 hasConceptScore W4319986212C111472728 @default.
- W4319986212 hasConceptScore W4319986212C119857082 @default.
- W4319986212 hasConceptScore W4319986212C121332964 @default.
- W4319986212 hasConceptScore W4319986212C136389625 @default.
- W4319986212 hasConceptScore W4319986212C136764020 @default.
- W4319986212 hasConceptScore W4319986212C138885662 @default.
- W4319986212 hasConceptScore W4319986212C153083717 @default.
- W4319986212 hasConceptScore W4319986212C154945302 @default.
- W4319986212 hasConceptScore W4319986212C15744967 @default.
- W4319986212 hasConceptScore W4319986212C173853756 @default.
- W4319986212 hasConceptScore W4319986212C174348530 @default.
- W4319986212 hasConceptScore W4319986212C17744445 @default.
- W4319986212 hasConceptScore W4319986212C185429906 @default.
- W4319986212 hasConceptScore W4319986212C199539241 @default.
- W4319986212 hasConceptScore W4319986212C2776321320 @default.
- W4319986212 hasConceptScore W4319986212C2776548248 @default.
- W4319986212 hasConceptScore W4319986212C2777200299 @default.
- W4319986212 hasConceptScore W4319986212C2779530757 @default.
- W4319986212 hasConceptScore W4319986212C2781181686 @default.
- W4319986212 hasConceptScore W4319986212C31258907 @default.
- W4319986212 hasConceptScore W4319986212C33923547 @default.
- W4319986212 hasConceptScore W4319986212C41008148 @default.
- W4319986212 hasConceptScore W4319986212C46312422 @default.
- W4319986212 hasConceptScore W4319986212C50644808 @default.
- W4319986212 hasConceptScore W4319986212C62520636 @default.
- W4319986212 hasLocation W43199862121 @default.
- W4319986212 hasLocation W43199862122 @default.
- W4319986212 hasOpenAccess W4319986212 @default.
- W4319986212 hasPrimaryLocation W43199862121 @default.
- W4319986212 hasRelatedWork W2947809439 @default.
- W4319986212 hasRelatedWork W2971034786 @default.
- W4319986212 hasRelatedWork W3011779917 @default.
- W4319986212 hasRelatedWork W3095538999 @default.
- W4319986212 hasRelatedWork W3153922349 @default.
- W4319986212 hasRelatedWork W3162567751 @default.
- W4319986212 hasRelatedWork W3210156800 @default.
- W4319986212 hasRelatedWork W4221088574 @default.
- W4319986212 hasRelatedWork W4226172683 @default.
- W4319986212 hasRelatedWork W4249546094 @default.
- W4319986212 isParatext "false" @default.
- W4319986212 isRetracted "false" @default.
- W4319986212 workType "article" @default.