C5L7: A Zero-Shot Algorithm for Intent and Slot Detection in Multilingual Task Oriented Languages

Abstract

Voice assistants are becoming central to our lives. The convenience of using voice assistants to do simple tasks has created an industry for voice-enabled devices like TVs, thermostats, air conditioners, etc. It has also improved the quality of life of elders by making the world more accessible. Voice assistants engage in task-oriented dialogues using machine-learned language understanding models. However, training deep-learned models take a lot of training data, which is time-consuming and expensive. Furthermore, it is even more problematic if we want the voice assistant to understand hundreds of languages. In this paper, we present a zero-shot deep learning algorithm that uses only the English part of the Massive dataset and achieves a high level of accuracy across 51 languages. The algorithm uses delexicalized translation to generate a multilingual parallel corpus with intent and slot labels for data augmentation. The training data is further weighted to improve the accuracy of the worst-performing languages. We report on our experiments with code-switching, word order, multilingual ensemble methods and other techniques and their impact on overall accuracy.