A Semi-Supervised Approach for Low-Resourced Text Generation

TL;DR

This paper introduces a semi-supervised method utilizing unlabeled data with denoising auto-encoders and reinforcement learning to improve low-resource text generation tasks, demonstrating significant performance gains.

Contribution

It presents a novel semi-supervised approach combining DAE and RL to leverage unlabeled data for low-resource text generation, which is adaptable across various tasks.

Findings

Significant performance improvements over basic models

Effective use of unlabeled data in low-resource settings

Adaptability across different text generation tasks

Abstract

Recently, encoder-decoder neural models have achieved great success on text generation tasks. However, one problem of this kind of models is that their performances are usually limited by the scale of well-labeled data, which are very expensive to get. The low-resource (of labeled data) problem is quite common in different task generation tasks, but unlabeled data are usually abundant. In this paper, we propose a method to make use of the unlabeled data to improve the performance of such models in the low-resourced circumstances. We use denoising auto-encoder (DAE) and language model (LM) based reinforcement learning (RL) to enhance the training of encoder and decoder with unlabeled data. Our method shows adaptability for different text generation tasks, and makes significant improvements over basic text generation models.