This paper presents an empirical study of conversational question reformulation (CQR) with sequence-to-sequence architectures and pretrained language models (PLMs). We leverage PLMs to address the strong token-to-token independence assumption made in the common objective, maximum likelihood estimation, for the CQR task. In CQR benchmarks of task-oriented dialogue systems, we evaluate fine-tuned PLMs on the recently-introduced CANARD dataset as an in-domain task and validate the models using data from the TREC 2019 CAsT Track as an out-domain task. Examining a variety of architectures with different numbers of parameters, we demonstrate that the recent text-to-text transfer transformer (T5) achieves the best results both on CANARD and CAsT with fewer parameters, compared to similar transformer architectures.
@article{arxiv.2004.01909,
title = {Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models},
author = {Sheng-Chieh Lin and Jheng-Hong Yang and Rodrigo Nogueira and Ming-Feng Tsai and Chuan-Ju Wang and Jimmy Lin},
journal= {arXiv preprint arXiv:2004.01909},
year = {2020}
}