Selective Token Generation for Few-shot Natural Language Generation

TL;DR

This paper introduces a reinforcement learning-based method for selective token generation that improves few-shot natural language generation by allowing a task-specific adapter and a pre-trained language model to collaborate more effectively.

Contribution

It proposes a novel RL-based selective token generation algorithm that enhances the robustness and stability of few-shot NLG by dynamically choosing tokens from the PLM and adapter.

Findings

Significantly outperforms previous additive learning algorithms on various NLG tasks.

Improves robustness to overfitting in few-shot settings.

Enhances stability of RL training in language generation.

Abstract

Natural language modeling with limited training data is a challenging problem, and many algorithms make use of large-scale pretrained language models (PLMs) for this due to its great generalization ability. Among them, additive learning that incorporates a task-specific adapter on top of the fixed large-scale PLM has been popularly used in the few-shot setting. However, this added adapter is still easy to disregard the knowledge of the PLM especially for few-shot natural language generation (NLG) since an entire sequence is usually generated by only the newly trained adapter. Therefore, in this work, we develop a novel additive learning algorithm based on reinforcement learning (RL) that selectively outputs language tokens between the task-general PLM and the task-specific adapter during both training and inference. This output token selection over the two generators allows the adapter to take into account solely the task-relevant parts in sequence generation, and therefore makes it more robust to overfitting as well as more stable in RL training. In addition, to obtain the complementary adapter from the PLM for each few-shot task, we exploit a separate selecting module that is also simultaneously trained using RL. Experimental results on various few-shot NLG tasks including question answering, data-to-text generation and text summarization demonstrate that the proposed selective token generation significantly outperforms the previous additive learning algorithms based on the PLMs.