DOMAIN ADAPTATION VIA DISTRIBUTION AND REPRESENTATION MATCHING: A CASE STUDY ON TRAINING DATA SELECTION VIA REINFORCEMENT LEARNING

Miaofeng Liu, Yan Song, Hongbin Zou, Tong Zhang

Abstract: Supervised models suffer from domain shifting where distribution mismatch across domains greatly affect model performance. Particularly, noise scattered in each domain has played a crucial role in representing such distribution, especially in various natural language processing (NLP) tasks. In addressing this issue, training data selection (TDS) has been proven to be a prospective way to train supervised models with higher performance and efficiency. Following the TDS methodology, in this paper, we propose a general data selection framework with representation learning and distribution matching simultaneously for domain adaptation on neural models. In doing so, we formulate TDS as a novel selection process based on a learned distribution from the input data, which is produced by a trainable selection distribution generator (SDG) that is optimized by reinforcement learning (RL). Then, the model trained by the selected data not only predicts the target domain data in a specific task, but also provides input for the value function of the RL. Experiments are conducted on three typical NLP tasks, namely, part-of-speech tagging, dependency parsing, and sentiment analysis. Results demonstrate the validity and effectiveness of our approach.

Keywords: domain adaptation, training data selection, reinforcement learning, natural language processing

TL;DR: Training data selection via reinforcement learning