Multi-Sentence Knowledge Selection in Open-Domain Dialogue
Incorporating external knowledge sources effectively in conversations is a longstanding problem in open-domain dialogue research. The existing literature on open-domain knowledge selection is limited and makes certain brittle assumptions on knowledge sources to simplify the overall task (Dinan et al., 2019), such as the existence of a single relevant knowledge sentence per context. In this work, we evaluate the existing state of open-domain conversation knowledge selection, showing where the existing methodologies regarding data and evaluation are flawed. We then improve on them by proposing a new framework for collecting relevant knowledge, and create an augmented dataset based on the Wizard of Wikipedia (WOW) corpus, which we call WOW++. WOW++ averages 8 relevant knowledge sentences per dialogue context, embracing the inherent ambiguity of open-domain dialogue knowledge selection. We then benchmark various knowledge ranking algorithms on this augmented dataset with both intrinsic evaluation and extrinsic measures of response quality, showing that neural rerankers that use WOW++ can outperform rankers trained on standard datasets.
Code (1)
Tasks
SentenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification proble…
Multi-Task LearningResponse GenerationSentenceEnhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification proble…
Multi-Task LearningResponse GenerationSentenceTradeoffs in Sentence Selection Techniques for Open-Domain Question Answering
Current methods in open-domain question answering (QA) usually employ a pipeline of first retrieving relevant documents, then applying strong reading comprehension (RC) models to that retrieved text. However, modern RC m…
Open-Domain Question AnsweringQuestion AnsweringReading ComprehensionRetrieval+2Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation
Open-Domain Generative Question Answering has achieved impressive performance in English by combining document-level retrieval with answer generation. These approaches, which we refer to as GenQA, can generate complete s…
Answer GenerationGenerative Question AnsweringOpen-Domain Question AnsweringQuestion Answering+2Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering
Open Domain Question Answering requires systems to retrieve external knowledge and perform multi-hop reasoning by composing knowledge spread over multiple sentences. In the recently introduced open domain question answer…
Information RetrievalOpen-Domain Question AnsweringQuestion AnsweringRetrieval