ISCA Archive Interspeech 2014
ISCA Archive Interspeech 2014

Detecting out-of-domain utterances addressed to a virtual personal assistant

Gokhan Tur, Anoop Deoras, Dilek Hakkani-Tür

Using different sources of information for grammar induction results in grammars that vary in coverage and precision. Fusing such grammars with a strategy that exploits their strengths while minimizing their weaknesses is expected to produce grammars with superior performance. We focus on the fusion of grammars produced using a knowledge-based approach using lexicalized ontologies and a data-driven approach using semantic similarity clustering. We propose various algorithms for finding the mapping between the (non-terminal) rules generated by each grammar induction algorithm, followed by rule fusion. Three fusion approaches are investigated: early, mid and late fusion. Results show that late fusion provides the best relative F-measure performance improvement by 20%.


doi: 10.21437/Interspeech.2014-69

Cite as: Tur, G., Deoras, A., Hakkani-Tür, D. (2014) Detecting out-of-domain utterances addressed to a virtual personal assistant. Proc. Interspeech 2014, 283-287, doi: 10.21437/Interspeech.2014-69

@inproceedings{tur14_interspeech,
  author={Gokhan Tur and Anoop Deoras and Dilek Hakkani-Tür},
  title={{Detecting out-of-domain utterances addressed to a virtual personal assistant}},
  year=2014,
  booktitle={Proc. Interspeech 2014},
  pages={283--287},
  doi={10.21437/Interspeech.2014-69},
  issn={2308-457X}
}