Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models
This work addresses improving question reformulation in task-oriented dialogue systems, but it is incremental as it applies existing methods to new datasets.
The paper tackled conversational question reformulation by fine-tuning pretrained language models, showing that T5 achieved the best results on CANARD and CAsT benchmarks with fewer parameters.
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.