Abstract
This paper presents a dialog state tracker submitted to Dialog State Tracking Challenge 5 (DSTC 5) with details. To tackle the challenging cross-language human-human dialog state tracking task with limited training data, we propose a tracker that focuses on words with meaningful context based on attention mechanism and bi-directional long short term memory (LSTM). The vocabulary including a plenty of proper nouns is vectorized with a sufficient amount of related texts crawled from web to learn a good embedding for words not existent in training dialogs. Despite its simplicity, our proposed tracker succeeded to achieve high accuracy without sophisticated pre- and post-processing.
Original language | English |
---|---|
Title of host publication | 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 531-537 |
Number of pages | 7 |
ISBN (Electronic) | 9781509049035 |
DOIs | |
Publication status | Published - 2017 Feb 7 |
Externally published | Yes |
Event | 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - San Diego, United States Duration: 2016 Dec 13 → 2016 Dec 16 |
Publication series
Name | 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings |
---|
Conference
Conference | 2016 IEEE Workshop on Spoken Language Technology, SLT 2016 |
---|---|
Country/Territory | United States |
City | San Diego |
Period | 16/12/13 → 16/12/16 |
Bibliographical note
Publisher Copyright:© 2016 IEEE.
Keywords
- Attention mechanism
- Dialog state tracking
- DSTC5
- Recurrent Neural Network
- Word embedding
ASJC Scopus subject areas
- Human-Computer Interaction
- Artificial Intelligence
- Language and Linguistics
- Computer Vision and Pattern Recognition
- Computer Science Applications