Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963827272> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2963827272 abstract "We present a method for inducing new dialogue systems from very small amounts of unannotated dialogue data, showing how word-level exploration using Reinforcement Learning (RL), combined with an incremental and semantic grammar - Dynamic Syntax (DS) - allows systems to discover, generate, and understand many new dialogue variants. The method avoids the use of expensive and time-consuming dialogue act annotations, and supports more natural (incremental) dialogues than turn-based systems. Here, language generation and dialogue management are treated as a joint decision/optimisation problem, and the MDP model for RL is constructed automatically. With an implemented system, we show that this method enables a wide range of dialogue variations to be automatically captured, even when the system is trained from only a single dialogue. The variants include question-answer pairs, over- and under-answering, self- and other-corrections, clarification interaction, split-utterances, and ellipsis. This generalisation property results from the structural knowledge and constraints present within the DS grammar, and highlights some limitations of recent systems built using machine learning techniques only." @default.
- W2963827272 created "2019-07-30" @default.
- W2963827272 creator A5010949145 @default.
- W2963827272 creator A5013679563 @default.
- W2963827272 creator A5076494767 @default.
- W2963827272 date "2016-12-01" @default.
- W2963827272 modified "2023-09-24" @default.
- W2963827272 title "Bootstrapping incremental dialogue systems: using linguistic knowledge to learn from minimal data" @default.
- W2963827272 hasPublicationYear "2016" @default.
- W2963827272 type Work @default.
- W2963827272 sameAs 2963827272 @default.
- W2963827272 citedByCount "10" @default.
- W2963827272 countsByYear W29638272722017 @default.
- W2963827272 countsByYear W29638272722019 @default.
- W2963827272 crossrefType "proceedings-article" @default.
- W2963827272 hasAuthorship W2963827272A5010949145 @default.
- W2963827272 hasAuthorship W2963827272A5013679563 @default.
- W2963827272 hasAuthorship W2963827272A5076494767 @default.
- W2963827272 hasConcept C106159729 @default.
- W2963827272 hasConcept C111472728 @default.
- W2963827272 hasConcept C138885662 @default.
- W2963827272 hasConcept C154945302 @default.
- W2963827272 hasConcept C162324750 @default.
- W2963827272 hasConcept C189950617 @default.
- W2963827272 hasConcept C195324797 @default.
- W2963827272 hasConcept C204321447 @default.
- W2963827272 hasConcept C207609745 @default.
- W2963827272 hasConcept C26022165 @default.
- W2963827272 hasConcept C41008148 @default.
- W2963827272 hasConcept C41895202 @default.
- W2963827272 hasConcept C44291984 @default.
- W2963827272 hasConcept C60048249 @default.
- W2963827272 hasConcept C90805587 @default.
- W2963827272 hasConcept C97541855 @default.
- W2963827272 hasConceptScore W2963827272C106159729 @default.
- W2963827272 hasConceptScore W2963827272C111472728 @default.
- W2963827272 hasConceptScore W2963827272C138885662 @default.
- W2963827272 hasConceptScore W2963827272C154945302 @default.
- W2963827272 hasConceptScore W2963827272C162324750 @default.
- W2963827272 hasConceptScore W2963827272C189950617 @default.
- W2963827272 hasConceptScore W2963827272C195324797 @default.
- W2963827272 hasConceptScore W2963827272C204321447 @default.
- W2963827272 hasConceptScore W2963827272C207609745 @default.
- W2963827272 hasConceptScore W2963827272C26022165 @default.
- W2963827272 hasConceptScore W2963827272C41008148 @default.
- W2963827272 hasConceptScore W2963827272C41895202 @default.
- W2963827272 hasConceptScore W2963827272C44291984 @default.
- W2963827272 hasConceptScore W2963827272C60048249 @default.
- W2963827272 hasConceptScore W2963827272C90805587 @default.
- W2963827272 hasConceptScore W2963827272C97541855 @default.
- W2963827272 hasLocation W29638272721 @default.
- W2963827272 hasOpenAccess W2963827272 @default.
- W2963827272 hasPrimaryLocation W29638272721 @default.
- W2963827272 hasRelatedWork W1491700729 @default.
- W2963827272 hasRelatedWork W1530250655 @default.
- W2963827272 hasRelatedWork W1536743489 @default.
- W2963827272 hasRelatedWork W1541013760 @default.
- W2963827272 hasRelatedWork W1560002237 @default.
- W2963827272 hasRelatedWork W1567146190 @default.
- W2963827272 hasRelatedWork W1578533525 @default.
- W2963827272 hasRelatedWork W1792761184 @default.
- W2963827272 hasRelatedWork W2120614088 @default.
- W2963827272 hasRelatedWork W2126814423 @default.
- W2963827272 hasRelatedWork W2277540893 @default.
- W2963827272 hasRelatedWork W2308941328 @default.
- W2963827272 hasRelatedWork W2340308465 @default.
- W2963827272 hasRelatedWork W250521078 @default.
- W2963827272 hasRelatedWork W2911595932 @default.
- W2963827272 hasRelatedWork W2963281204 @default.
- W2963827272 hasRelatedWork W3035706973 @default.
- W2963827272 hasRelatedWork W3098682828 @default.
- W2963827272 hasRelatedWork W3175591469 @default.
- W2963827272 hasRelatedWork W3211080179 @default.
- W2963827272 isParatext "false" @default.
- W2963827272 isRetracted "false" @default.
- W2963827272 magId "2963827272" @default.
- W2963827272 workType "article" @default.