A Novel Multi-Task Learning Framework for Semi-Supervised Semantic Parsing

doi:10.1109/TASLP.2020.3018233

A Novel Multi-Task Learning Framework for Semi-Supervised Semantic Parsing

2020-01-01

4

PRE

AI

DOI：10.1109/TASLP.2020.3018233

原文链接

原文求助

摘要

En 中文

While sequence-to-sequence (seq2seq) models on semantic parsing have demonstrated significant performance, the need for large amounts of labeled data still hinders the application of this technology to resource-poor domains. In this work, we work on alleviating data scarcity in semantic parsing. We propose a semi-supervised semantic parsing methods by exploiting unlabeled natural utterances in a novel multi-task learning framework. Two strategies are proposed. The first one takes entity sequences as training targets to improve the representations of encoder and reduce entity-mistakes in prediction. The second one extends Mean Teacher to seq2seq model and generates more target-side data to improve the generalizability of decoder network. Experiments demonstrate that our proposed methods significantly outperform the supervised baseline and achieve more impressive improvement than previous methods.

Keyword:

Semantics

Task analysis

Decoding

Training

Natural languages

Speech processing

Semisupervised learning

Semantic parsing

data scarcity

multi-task learning

semi-supervised learning

A Novel Multi-Task Learning Framework for Semi-Supervised Semantic Parsing

摘要

AI总结

期刊

机构

引用论文