Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models

Abstract

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.

References in corpus (1)

• Quasar: Datasets for Question Answering by Search and Reading

Cited by in corpus (5)

• Improving Conversational Passage Re-ranking with View Ensemble
• Knowledge-driven Answer Generation for Conversational Search
• BERT Embeddings Can Track Context in Conversational Search
• Learning to Ask Conversational Questions by Optimizing Levenshtein Distance
• Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering