Spoken language understanding from unaligned data using discriminative classification models

François Mairesse, Milica Gasic, Filip Jurcícek, Simon Keizer, Blaise Thomson, Kai Yu, Steve J. Young

Abstract

While data-driven methods for spoken language understanding reduce maintenance and portability costs compared with handcrafted parsers, the collection of word-level semantic annotations for training remains a time-consuming task. A recent line of research has focused on building generative models from unaligned semantic representations, using expectation-maximisation techniques to align semantic concepts. This paper presents an efficient, simple technique that parses a semantic tree by recursively calling discriminative semantic classification models. Results show that it outperforms methods based on the Hidden Vector State model and Markov Logic Networks, while performance is close to more complex grammar induction techniques. We also show that our method is robust to speech recognition errors, by improving over a handcrafted parser previously used for dialogue data collection.
BibTeX
@inproceedings{mairesse2009spoken,
  author = {François Mairesse and Milica Gasic and Filip Jurcícek and Simon Keizer and Blaise Thomson and Kai Yu and Steve J. Young},
  title = {{Spoken language understanding from unaligned data using discriminative classification models}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2009},
  doi = {10.1109/icassp.2009.4960692},
}

Loading related content...

Figure