Abstract
We present a new neural architecture for wide-coverage Natural Language Understanding in Spoken Dialogue Systems. We develop a hierarchical multi-task architecture, which delivers a multi-layer representation of sentence meaning (i.e., Dialogue Acts and Frame-like structures). The architecture is a hierarchy of self-attention mechanisms and BiLSTM encoders followed by CRF tagging layers. We describe a variety of experiments, showing that our approach obtains promising results on a dataset annotated with Dialogue Acts and Frame Semantics. Moreover, we demonstrate its applicability to a different, publicly available NLU dataset annotated with domain-specific intents and corresponding semantic roles, providing overall performance higher than state-of-the-art tools such as RASA, Dialogflow, LUIS, and Watson. For example, we show an average 4.45% improvement in entity tagging F-score over Rasa, Dialogflow and LUIS.
Original language | English |
---|---|
Title of host publication | Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue |
Publisher | Association for Computational Linguistics |
Pages | 254-263 |
Number of pages | 10 |
ISBN (Electronic) | 9781950737611 |
DOIs | |
Publication status | Published - Sept 2019 |
Event | 20th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2019 - Stockholm, Sweden Duration: 11 Sept 2019 → 13 Sept 2019 |
Conference
Conference | 20th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2019 |
---|---|
Abbreviated title | SIGDIAL 2019 |
Country/Territory | Sweden |
City | Stockholm |
Period | 11/09/19 → 13/09/19 |
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Computer Vision and Pattern Recognition
- Human-Computer Interaction
- Modelling and Simulation