Capturing Conversational Interaction for Question Answering via Global History Reasoning
Jin Qian, Bowei Zou, Mengxing Dong, Xiao Li, AiTi Aw, Yu Hong
Abstract
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 multi-turn 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.
BibTeX
@inproceedings{qian-etal-2022-capturing,
title = "Capturing Conversational Interaction for Question Answering via Global History Reasoning",
author = "Qian, Jin and
Zou, Bowei and
Dong, Mengxing and
Li, Xiao and
Aw, AiTi and
Hong, Yu",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.159/",
doi = "10.18653/v1/2022.findings-naacl.159",
pages = "2071--2078"
}