In this work, we study how the finetuning stage in the pretrain-finetune framework changes the behavior of a pretrained neural language generator. We focus on the transformer encoder-decoder model for the open-domain dialogue response generation task. Our major finding is that after standard finetuning, the model forgets some of the important language generation skills acquired during large-scale pretraining. We demonstrate the forgetting phenomenon through a set of detailed behavior analysis from the perspectives of knowledge transfer, context sensitivity, and function space projection. As a preliminary attempt to alleviate the forgetting problem, we propose an intuitive finetuning strategy named "mix-review". We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent. Finally, we discuss interesting behavior of the resulting dialogue model and its implications.
@article{arxiv.1910.07117,
title = {Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models},
author = {Tianxing He and Jun Liu and Kyunghyun Cho and Myle Ott and Bing Liu and James Glass and Fuchun Peng},
journal= {arXiv preprint arXiv:1910.07117},
year = {2021}
}