End-to-end response selection based on multi-level context response matching. (September 2020)

• Record Type: Journal Article
• Authors: Boussaha, Basma El Amel; Hernandez, Nicolas; Jacquin, Christine; Morin, Emmanuel
• Is Part Of: Computer speech & language. Volume 63(2020)
• Publication Date: 2020-09
• Subjects: Retrieval systems -- Chatbots -- Neural networks -- Goal-oriented dialogue systems -- DSTC; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2020.101080
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: We proposed a simple but efficient retrieval-based dialogue system. By matching the context with the candidate response on the sequence and word levels, the system achieves the best performance. The error analysis reveals the importance of annotating negative responses instead of randomly selecting them. The evaluation of our system on other benchmark datasets show the efficiency of our approach compared to the state-of-the-art systems. Abstract: This paper presents our work on the Dialog System Technology Challenges 7 (DSTC7). We took part in Track 1 on sentence selection which evaluates response retrieving in dialog systems on more realistic test scenarios compared to the state-of-the-art evaluations. Our proposed dialog system matches the context with the best response by computing their semantic similarity on word and sequence levels. Evaluation results on the datasets provided show the effectiveness of our system by achieving higher performance compared to the provided baseline system. Our system enjoys the advantages of its simple and end-to-end architecture making its training and adaptation to other domains easier.