Matrix Factorization with Knowledge Graph Propagation for Unsupervised Spoken Language Understanding

@inproceedings{Chen2015MatrixFW,
  title={Matrix Factorization with Knowledge Graph Propagation for Unsupervised Spoken Language Understanding},
  author={Yun-Nung Chen and William Yang Wang and Anatole Gershman and Alexander I. Rudnicky},
  booktitle={ACL},
  year={2015}
}
Spoken dialogue systems (SDS) typically require a predefined semantic ontology to train a spoken language understanding (SLU) module. In addition to the annotation cost, a key challenge for designing such an ontology is to define a coherent slot set while considering their complex relations. This paper introduces a novel matrix factorization (MF) approach to learn latent feature vectors for utterances and semantic elements without the need of corpus annotations. Specifically, our model learns… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 21 CITATIONS

Unsupervised user intent modeling by feature-enriched matrix factorization

  • 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2016
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS

Encoding Module ( you ) tell vivian be quietto ROOT ( imperative )

Yun-Nung Chen, Dilek Hakanni-Tür, +3 authors Li Deng
  • 2016
VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 46 REFERENCES

Dependency-Based Word Embeddings

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Discriminative spoken language understanding using word confusion networks

  • 2012 IEEE Spoken Language Technology Workshop (SLT)
  • 2012
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

An empirical investigation of sparse log-linear models for improved dialogue act classification

  • 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2013
VIEW 6 EXCERPTS