Empirical feature analysis for dialogue breakdown detection*. (March 2019)

• Record Type: Journal Article
• Authors: Sugiyama, Hiroaki
• Is Part Of: Computer speech & language. Volume 54(2019)
• Page Start: 140
• Page End: 150
• Publication Date: 2019-03
• Subjects: Dialogue breakdown detection -- Chat-oriented dialogue system -- Feature analysis; 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.2018.09.007
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: Dialogue-act is a key feature to detect dialogue breakdown. Sentence fluency and seq2seq embedding vectors improve performance. Our model almost reaches the upper bound in accuracy but far from it in MSE/JSD. Abstract: Chat-oriented dialogue systems sometimes generate inappropriate response utterances to user utterances that cause dialogue breakdown. Detecting such inappropriate utterances and suppressing them will support the continuation of the dialogue. Although a previous state-of-the-art dialogue breakdown detector leveraged dialogue-act transitions and word-based similarities between utterance pairs, these features are insufficient to evaluate the appropriateness of question-answering or relatedness between utterances that share few topic words. In this paper, we propose novel features to assess these problems, and examine their effectiveness for improving the performance of dialogue breakdown detection.