# Robust Spoken Language Understanding via Paraphrasing

arXiv: https://arxiv.org/abs/1809.06444 · HTML: https://mlsanity.com/paper/1809.06444/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2018.

## Built on by (most cited first, 1 of 1)

- [A survey of joint intent detection and slot-filling models in natural language understanding](https://mlsanity.com/paper/2101.08091/) (2021)

## Abstract (arXiv)

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.