Abstract
This paper presents a hybrid dialog state tracker enhanced by trainable Spoken Language Understanding (SLU) for slot-filling dialog systems. Our architecture is inspired by previously proposed neural-network-based belief-tracking systems. In addition, we extended some parts of our modular architecture with differentiable rules to allow end-to-end training. We hypothesize that these rules allow our tracker to generalize better than pure machine-learning based systems. For evaluation, we used the Dialog State Tracking Challenge (DSTC) 2 dataset - a popular belief tracking testbed with dialogs from restaurant information system. To our knowledge, our hybrid tracker sets a new state-of-the-art result in three out of four categories within the DSTC2.- Anthology ID:
- E17-2033
- Volume:
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 205–210
- Language:
- URL:
- https://aclanthology.org/E17-2033
- DOI:
- Cite (ACL):
- Miroslav Vodolán, Rudolf Kadlec, and Jan Kleindienst. 2017. Hybrid Dialog State Tracker with ASR Features. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 205–210, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- Hybrid Dialog State Tracker with ASR Features (Vodolán et al., EACL 2017)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/E17-2033.pdf