Multi-domain spoken language understanding with transfer learning
Speech Communication
Hybrid approach to robust dialog management using agenda and dialog examples
Computer Speech and Language
Hybrid user intention modeling to diversify dialog simulations
Computer Speech and Language
A joint model for discovery of aspects in utterances
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
| Hi-index | 0.00 |
Sequential modeling is a fundamental task in scientific fields, especially in speech and natural language processing, where many problems of sequential data can be cast as a sequential labeling or a sequence classification. In many applications, the two problems are often correlated, for example named entity recognition and dialog act classification for spoken language understanding. This paper presents triangular-chain conditional random fields (CRFs), a unified probabilistic model combining two related problems. Triangular-chain CRFs jointly represent the sequence and meta-sequence labels in a single graphical structure that both explicitly encodes their dependencies and preserves uncertainty between them. An efficient inference and parameter estimation method is described for triangular-chain CRFs by extending linear-chain CRFs. This method outperforms baseline models on synthetic data and real-world dialog data for spoken language understanding.