Show simple item record

dc.contributor.advisor Thayasivam U
dc.contributor.author Bhathiya HS
dc.date.accessioned 2020
dc.date.available 2020
dc.date.issued 2020
dc.identifier.uri http://dl.lib.uom.lk/handle/123/17699
dc.description.abstract Despite ground breaking work in the academia, current state-of-the-art work in goal-oriented conversational-agents has not been able to fulfil the demand of the industry for multi-domain multi-lingual, adaptable, dialogue systems. Data-intensive nature of deep learning models used in dialogue state tracking (DST) module, which is a core component of the goal-oriented dialogue architecture, and the lack of large labelled dialogue corpus for state tracking are two main factors which have hindered the progress. We identified, modeling with separate natural language understanding (NLU) module and joint modeling of dialogue state tracker with NLU as the two main approaches for state tracking, and accordingly made two major contributions. First, we propose a novel meta-learning algorithm for intent detection and slot-filling tasks, focusing on models with separate NLU. Our work empirically demonstrates that the proposed meta-learning approach is capable of learning a meta-parameter(prior) from similar, but different tasks. Compared to the random initialization, which regular supervised learning algorithms rely on, proposed method significantly improves the accuracy in both intent detection and slot-filling tasks in few-shot (5-way 1-shot and 5-way 2-shot) settings. Further, our effective use of meta-learning for intent detection and slot-filling opens up new line of research for DST. Second, we systematically review the progression of joint NLU/DST models with special emphasis on their ability to generalize and adapt to new domains and languages. en_US
dc.language.iso en en_US
dc.subject DIALOGUE STATE TRACKING en_US
dc.subject NATURAL LANGUAGE UNDERSTANDING en_US
dc.subject JOINT INTENT DETECTION AND SLOT FILLING en_US
dc.subject META LEARNING en_US
dc.subject CONVERSATIONAL AI en_US
dc.subject COMPUTER SCIENCE – Dissertations en_US
dc.subject COMPUTER SCIENCE & ENGINEERING – Dissertations en_US
dc.title Dialogue state tracking for low-resource languages en_US
dc.type Thesis-Full-text en_US
dc.identifier.faculty Engineering en_US
dc.identifier.degree MSc in Computer Science & Engineering - By Research en_US
dc.identifier.department Department of Computer Science & Engineering en_US
dc.date.accept 2020
dc.identifier.accno TH4461 en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record