Extensions to hybrid code networks for FAIR dialog dataset. (January 2019)

• Record Type: Journal Article
• Authors: Ham, Jiyeon; Lim, Soohyun; Lee, Kyeng-Hun; Kim, Kee-Eung
• Is Part Of: Computer speech & language. Volume 53(2019)
• Page Start: 80
• Page End: 91
• Publication Date: 2019-01
• Subjects: Dialog systems technology -- Goal-oriented dialog system -- Extended hybrid code network -- DSTC6; 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.2018.07.004
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: The proposed system extends some of modules to be learned from data. The proposed system is adaptable to changes in the knowledge base. Extensions to hybrid code networks achieve the perfect accuracy in all DSTC6 test datasets. The source code is available for download from github. Abstract: Goal-oriented dialog systems require a different approach from chit-chat conversational systems in that they should perform various subtasks as well as continue the conversation itself. Since these systems typically interact with an external knowledge base that changes over time, it is desirable to incorporate domain knowledge to deal with such changes, yet with minimum human effort. This paper presents an extended version of the Hybrid Code Network (HCN) developed for the Facebook AI research (FAIR) dialog dataset used in the Sixth Dialog System Technology Challenge (DSTC6). Compared to the original HCN, the system was more adaptable to changes in the knowledge base due to the modules that are extended to be learned from data. Using the proposed learning scheme with fairly elementary domain-specific rules, the proposed model achieved 100% accuracy in all test datasets.