Robust Spoken Language Understanding via Paraphrasing

09/17/2018
by   Avik Ray, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/15/2019

Iterative Delexicalization for Improved Spoken Language Understanding

Recurrent neural network (RNN) based joint intent classification and slo...
research
06/24/2016

Sequential Convolutional Neural Networks for Slot Filling in Spoken Language Understanding

We investigate the usage of convolutional neural networks (CNNs) for the...
research
04/29/2020

Data Augmentation for Spoken Language Understanding via Pretrained Models

The training of spoken language understanding (SLU) models often faces t...
research
12/13/2020

C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling

Slot filling, a fundamental module of spoken language understanding, oft...
research
09/30/2019

Incremental processing of noisy user utterances in the spoken language understanding task

The state-of-the-art neural network architectures make it possible to cr...
research
10/16/2019

Joint Learning of Word and Label Embeddings for Sequence Labelling in Spoken Language Understanding

We propose an architecture to jointly learn word and label embeddings fo...
research
09/12/2016

Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks

Natural language understanding (NLU) is a core component of a spoken dia...

Please sign up or login with your details

Forgot password? Click here to reset