paper-with-me

Papers

Multi-Sentence Knowledge Selection in Open-Domain Dialogue

2022-03-01 · INLG (ACL) 2021 8 · Mihail Eric, Nicole Chartier, Behnam Hedayatnia, Karthik Gopalakrishnan, Pankaj Rajan, Yang Liu, Dilek Hakkani-Tur

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.

📄 PDF Abstract BibTeX arXiv:2203.00763

Code (1)

alexa/wow-plus-plus 공식 구현

Tasks

Sentence

Methods 이 논문이 사용한 방법론

Wizard Computer vision is an interesting tool for animal behavior monitoring, mainly because it limits animal handling and it can be used to record various traits using only one sensor.…

Similar Papers 제목 키워드 기반

Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs

2022-07-01 · NAACL 2022 7 · Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal 외

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 GenerationSentence

Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs

2022-06-15 · Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal 외

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 GenerationSentence

Tradeoffs in Sentence Selection Techniques for Open-Domain Question Answering

2020-09-18 · Shih-ting Lin, Greg Durrett

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+2

Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation

2021-10-14 · Benjamin Muller, Luca Soldaini, Rik Koncel-Kedziorski, Eric Lind 외

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+2

Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering

2020-04-07 · Pratyay Banerjee, Chitta Baral

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