Adversarial multi-task training method used for spoken language understanding

Abstract

The invention discloses an adversarial multi-task training method used for spoken language understanding. The method comprises the following steps that: carrying out sampling from unlabeled data and labeled data to train and update a language model and a shared space, labeling a first public characteristic obtained by the shared space as a language model task to train and update a task discriminator and the shared space; and carrying out sampling from the labeled data to train and update a spoken language understanding model and the shared space, and labeling a second public characteristic obtained by the shared space as a spoken language understanding task to train and update the task discriminator and the shared space. According to the adversarial multi-task training method, which is disclosed by the embodiment of the invention, used for spoken language understanding, the spoken language understanding model is trained simultaneously on the basis of the unlabeled data and the labeleddata, so that the heavy dependency of a traditional method used for training the spoken language understanding model on the labeled data is avoided, and cost expenditures caused by using a great quantity of labeled data are lowered.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an adversarial multi-task training method for spoken language comprehension. Background technique [0002] The spoken language understanding (SLU, spoken language understanding) module is a key component of the target-oriented spoken language dialogue system (SDS, spoken dialogue system), which parses the user's utterance into corresponding semantic concepts. For example, the sentence "show me flights from Boston to New York" could be parsed as (departure city=Boston, arrival city=New York). Generally, it is considered as a slot filling task, assigning each word in an utterance a predefined semantic slot label. [0003] Recent research on statistical slot filling in SLU has focused on recurrent neural networks (RNNs) and their extensions, such as long and short memory networks (LSTMs), codec models, etc. These traditional methods require a large amount of labele...

AI Technical Summary

Problems solved by technology

However, since data annotation is labor-intensive and time-consuming, it is difficult to obtain sufficient in-domain labeled data for training

Images