Self-supervised clarification question generation for ambiguous multi-turn conversation

Clarification Question Generation (CQG) aims to automatically generate clarification ques-tions to avoid misunderstanding. In this paper, we focus on generating clarification ques-tions in the scenario of ambiguous multi-turn conversation, which can be well applied to the interactive systems, e.g., dialogue systems and conversational recommendation sys-tems. As a novel direction, limited manual-annotated samples are available for CQG. Moreover, existing approaches mainly ignore the representation of ambiguous semantics and cannot deal with the Out-of-Vocabulary (OOV) problem in a good manner. To address the above issues, we propose a Self-supervised Hierarchical Pointer-generator model (SHiP) for this task. In detail, similar to the backbone Coarse-to-fine process of CQG, we first formulate two self-supervised learning pretext tasks, i.e., Dialogue History Prediction and Entity Name Prediction. Then, we incorporate a hierarchical Transformer mechanism and a pointer-generator mechanism to understand the ambiguous multi-turn conversations and solve the OOV problem. Finally, we propose an end-to-end co-training paradigm to train the pretext tasks and downstream tasks. We quantify the improvements of SHiP against the competitive baselines on a publicly available dataset CLAQUA, showing a gen-eral improvement of 6.75% and 3.91% over state-of-the-art baseline in terms of BLEU and ROUGE-L, respectively. (C) 2021 Elsevier Inc. All rights reserved.