Capturing Conversational Interaction for Question Answering via Global History Reasoning
Jin H. Qian, Bowei Zou, Mengxing Dong, Xiao Li, Ai Ti Aw, Hong Zhi Yu · Findings of the Association for Computational Linguistics: NAACL 2022 · 2022
Conversational Question Answering (ConvQA)is required to answer the current question, conditioned on the observable paragraph-level context and conversation history.Previous works have intensively studied history-dependent reasoning.They perceive and absorb topic-related information of prior utterances in the interactive encoding stage.It yielded significant improvement compared to history-independent reasoning.This paper further strengthens the ConvQA encoder by establishing long-distance dependency among global utterances in multiturn conversation.We use multi-layer transformers to resolve long-distance relationships, which potentially contribute to the reweighting of attentive information in historical utterances.Experiments on QuAC show that our method obtains a substantial improvement (1%), yielding the F1 score of 73.7%.All source codes are available at https://github.com/ jaytsien/GHR.