Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems
Kai Hua, Zhiyuan Feng, Chongyang Tao, Rui Yan, Lu Zhang
Abstract
Recently, knowledge-grounded conversations in the open domain gain great attention from researchers. Existing works on retrieval-based dialogue systems have paid tremendous efforts to utilize neural networks to build a matching model, where all of the context and knowledge contents are used to match the response candidate with various representation methods.
Topics & Concepts
Computer scienceOpen domainSelection (genetic algorithm)Context (archaeology)Matching (statistics)Domain knowledgeQuestion answeringRepresentation (politics)Knowledge extractionKnowledge-based systemsArtificial intelligenceDomain (mathematical analysis)Knowledge representation and reasoningInformation retrievalLawPolitical sciencePaleontologyStatisticsMathematicsMathematical analysisPoliticsBiologyTopic ModelingSpeech and dialogue systemsNatural Language Processing Techniques