A multi-scenario text generation method based on meta reinforcement learning

doi:10.1016/j.patrec.2022.11.031

A multi-scenario text generation method based on meta reinforcement learning

2023-01-01

3

PRE

AI

DOI：10.1016/j.patrec.2022.11.031

Original

Original request for help

Save

Abstract

En 中文

Multi-scenario text generation is an essential task in natural language generation because of the multi -scene interlaced property of real-world problems. Traditional methods typically train the multi-scenario text generation models based on maximum likelihood estimation, which may suffer from the problem of exposure bias. Reinforcement learning (RL) based text generation methods could mitigate the exposure bias problem to some extent. However, the RL-based text generation methods are limited to the single -scenario tasks, which cannot be straightforwardly generalized to new scenario tasks. To address this prob-lem, in this paper, we propose a multi-scenario text generation method based on meta RL (MetaRL-TG), which implements the method of model-agnostic meta-learning (MAML) in the framework of RL-based text generation. The proposed MetaRL-TG method first learns the initial parameters from multiple train-ing tasks, then fine-tunes them in the target task. Thus, the proposed method is expected to efficiently achieve high-quality generated text in the new scenario. Finally, the effectiveness and generalization ca-pability of the proposed method are demonstrated for eight scenarios through English test datasets.(c) 2022 Elsevier B.V. All rights reserved.

Keywords:

Text generation

Natural language processing

Reinforcement learning

Meta-reinforcement learning

Multi-scenario

A multi-scenario text generation method based on meta reinforcement learning

Abstract

Journal

Organization