Robust Spoken Language Understanding via Paraphrasing

Avik Ray, Yilin Shen, Hongxia Jin


Learning intents and slot labels from user utterances is a fundamental step in all spoken language understanding (SLU) and dialog systems. State-of-the-art neural network based methods, after deployment, often suffer from performance degradation on encountering paraphrased utterances and out-of-vocabulary words, rarely observed in their training set. We address this challenging problem by introducing a novel paraphrasing based SLU model which can be integrated with any existing SLU model in order to improve their overall performance. We propose two new paraphrase generators using RNN and sequence-to-sequence based neural networks, which are suitable for our application. Our experiments on existing benchmark and in house datasets demonstrate the robustness of our models to rare and complex paraphrased utterances, even under adversarial test distributions.


 DOI: 10.21437/Interspeech.2018-2358

Cite as: Ray, A., Shen, Y., Jin, H. (2018) Robust Spoken Language Understanding via Paraphrasing. Proc. Interspeech 2018, 3454-3458, DOI: 10.21437/Interspeech.2018-2358.


@inproceedings{Ray2018,
  author={Avik Ray and Yilin Shen and Hongxia Jin},
  title={Robust Spoken Language Understanding via Paraphrasing},
  year=2018,
  booktitle={Proc. Interspeech 2018},
  pages={3454--3458},
  doi={10.21437/Interspeech.2018-2358},
  url={http://dx.doi.org/10.21437/Interspeech.2018-2358}
}