Report
Improving Longer-range Dialogue State Tracking
| العنوان: | Improving Longer-range Dialogue State Tracking |
|---|---|
| المؤلفون: | Zhang, Ye, Cao, Yuan, Mahdieh, Mahdis, Zhao, Jeffrey, Wu, Yonghui |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning |
| الوصف: | Dialogue state tracking (DST) is a pivotal component in task-oriented dialogue systems. While it is relatively easy for a DST model to capture belief states in short conversations, the task of DST becomes more challenging as the length of a dialogue increases due to the injection of more distracting contexts. In this paper, we aim to improve the overall performance of DST with a special focus on handling longer dialogues. We tackle this problem from three perspectives: 1) A model designed to enable hierarchical slot status prediction; 2) Balanced training procedure for generic and task-specific language understanding; 3) Data perturbation which enhances the model's ability in handling longer conversations. We conduct experiments on the MultiWOZ benchmark, and demonstrate the effectiveness of each component via a set of ablation tests, especially on longer conversations. Comment: 10 pages |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2103.00109 |
| رقم الانضمام: | edsarx.2103.00109 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |