Iterative Delexicalization for Improved Spoken Language Understanding

TL;DR

This paper introduces an iterative delexicalization method that enhances spoken language understanding by accurately handling out-of-vocabulary slot values, leading to improved intent classification and slot tagging performance.

Contribution

The paper presents a novel iterative delexicalization algorithm that outperforms greedy approaches, especially for unseen slot values, improving RNN-based spoken language understanding models.

Findings

Significant performance gains on benchmark datasets.

Effective handling of out-of-vocabulary slot values.

Improved intent classification and slot tagging accuracy.

Abstract

Recurrent neural network (RNN) based joint intent classification and slot tagging models have achieved tremendous success in recent years for building spoken language understanding and dialog systems. However, these models suffer from poor performance for slots which often encounter large semantic variability in slot values after deployment (e.g. message texts, partial movie/artist names). While greedy delexicalization of slots in the input utterance via substring matching can partly improve performance, it often produces incorrect input. Moreover, such techniques cannot delexicalize slots with out-of-vocabulary slot values not seen at training. In this paper, we propose a novel iterative delexicalization algorithm, which can accurately delexicalize the input, even with out-of-vocabulary slot values. Based on model confidence of the current delexicalized input, our algorithm improves delexicalization in every iteration to converge to the best input having the highest confidence. We show on benchmark and in-house datasets that our algorithm can greatly improve parsing performance for RNN based models, especially for out-of-distribution slot values.