2019/07/24 by Prakhar Gupta, Gupta, Prakhar, Shikib Mehri +10 · 2 citations
Computer Science · Mathematics · #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Data mining #Dialog box #Domain (mathematical analysis) #FOS: Computer and information sciences #Information retrieval #Judgement #Machine learning #Mathematics #Multi-Agent Systems and Negotiation #Natural language processing #Open domain #Programming language #Quality (philosophy) #Set (abstract data type) #Speech and dialogue systems #Topic Modeling #World Wide Web #cs.CL
paper · pdf · doi:10.48550/arxiv.1907.10568
published in arXiv (Cornell University) (Cornell University) · SIGDIAL 2019
openalex publication_date 2019/07/24 · arxiv created 2019/09/08 · arxiv updated 2019/09/10 · openalex created_date 2022/07/28 · openalex updated_date 2026/08/05
The aim of this paper is to mitigate the shortcomings of automatic evaluation of open-domain dialog systems through multi-reference evaluation. Existing metrics have been shown to correlate poorly with human judgement, particularly in open-domain dialog. One alternative is to collect human annotations for evaluation, which can be expensive and time consuming. To demonstrate the effectiveness of multi-reference evaluation, we augment the test set of DailyDialog with multiple references. A series of experiments show that the use of multiple references results in improved correlation between several automatic metrics and human judgement for both the quality and the diversity of system output.