SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking
| Autor: | Hwaran Lee, Tae-Yoon Kim, Jinsik Lee |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Matching (statistics) Computer Science - Machine Learning Computer Science - Computation and Language Computer science Speech recognition 010501 environmental sciences Ontology (information science) 01 natural sciences Domain (software engineering) Machine Learning (cs.LG) 030507 speech-language pathology & audiology 03 medical and health sciences Scalability Probability distribution Dialog box 0305 other medical science Computation and Language (cs.CL) Utterance 0105 earth and related environmental sciences |
| Zdroj: | ACL (1) |
| Popis: | In goal-oriented dialog systems, belief trackers estimate the probability distribution of slot-values at every dialog turn. Previous neural approaches have modeled domain- and slot-dependent belief trackers, and have difficulty in adding new slot-values, resulting in lack of flexibility of domain ontology configurations. In this paper, we propose a new approach to universal and scalable belief tracker, called slot-utterance matching belief tracker (SUMBT). The model learns the relations between domain-slot-types and slot-values appearing in utterances through attention mechanisms based on contextual semantic vectors. Furthermore, the model predicts slot-value labels in a non-parametric way. From our experiments on two dialog corpora, WOZ 2.0 and MultiWOZ, the proposed model showed performance improvement in comparison with slot-dependent methods and achieved the state-of-the-art joint accuracy. 6 pages, 2 figures, The 57th Annual Meeting of the Association for Computational Linguistics (ACL) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|