@inproceedings{bai-etal-2024-auto,
title = "Auto-{ACE}: An Automatic Answer Correctness Evaluation Method for Conversational Question Answering",
author = "Bai, Zhixin and
Wang, Bingbing and
Liang, Bin and
Xu, Ruifeng",
editor = "Wong, Kam-Fai and
Zhang, Min and
Xu, Ruifeng and
Li, Jing and
Wei, Zhongyu and
Gui, Lin and
Liang, Bin and
Zhao, Runcong",
booktitle = "Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sighan-1.9",
pages = "80--87",
abstract = "Conversational question answering aims to respond to questions based on relevant contexts and previous question-answer history. Existing studies typically use ground-truth answers in history, leading to the inconsistency between the training and inference phases. However, in real-world scenarios, progress in question answering can only be made using predicted answers. Since not all predicted answers are correct, indiscriminately using all predicted answers for training introduces noise into the model. To tackle these challenges, we propose an automatic answer correctness evaluation method named **Auto-ACE**. Specifically, we first construct an Att-BERT model which employs attention weight to the BERT model, so as to bridge the relation between the current question and the question-answer pair in history. Furthermore, to reduce the interference of the irrelevant information in the predicted answer, A-Scorer, an answer scorer is designed to evaluate the confidence of the predicted answer. We conduct a series of experiments on QuAC and CoQA datasets, and the results demonstrate the effectiveness and practicality of our proposed Auto-ACE framework.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bai-etal-2024-auto">
<titleInfo>
<title>Auto-ACE: An Automatic Answer Correctness Evaluation Method for Conversational Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhixin</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bingbing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongyu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Runcong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conversational question answering aims to respond to questions based on relevant contexts and previous question-answer history. Existing studies typically use ground-truth answers in history, leading to the inconsistency between the training and inference phases. However, in real-world scenarios, progress in question answering can only be made using predicted answers. Since not all predicted answers are correct, indiscriminately using all predicted answers for training introduces noise into the model. To tackle these challenges, we propose an automatic answer correctness evaluation method named **Auto-ACE**. Specifically, we first construct an Att-BERT model which employs attention weight to the BERT model, so as to bridge the relation between the current question and the question-answer pair in history. Furthermore, to reduce the interference of the irrelevant information in the predicted answer, A-Scorer, an answer scorer is designed to evaluate the confidence of the predicted answer. We conduct a series of experiments on QuAC and CoQA datasets, and the results demonstrate the effectiveness and practicality of our proposed Auto-ACE framework.</abstract>
<identifier type="citekey">bai-etal-2024-auto</identifier>
<location>
<url>https://aclanthology.org/2024.sighan-1.9</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>80</start>
<end>87</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Auto-ACE: An Automatic Answer Correctness Evaluation Method for Conversational Question Answering
%A Bai, Zhixin
%A Wang, Bingbing
%A Liang, Bin
%A Xu, Ruifeng
%Y Wong, Kam-Fai
%Y Zhang, Min
%Y Xu, Ruifeng
%Y Li, Jing
%Y Wei, Zhongyu
%Y Gui, Lin
%Y Liang, Bin
%Y Zhao, Runcong
%S Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F bai-etal-2024-auto
%X Conversational question answering aims to respond to questions based on relevant contexts and previous question-answer history. Existing studies typically use ground-truth answers in history, leading to the inconsistency between the training and inference phases. However, in real-world scenarios, progress in question answering can only be made using predicted answers. Since not all predicted answers are correct, indiscriminately using all predicted answers for training introduces noise into the model. To tackle these challenges, we propose an automatic answer correctness evaluation method named **Auto-ACE**. Specifically, we first construct an Att-BERT model which employs attention weight to the BERT model, so as to bridge the relation between the current question and the question-answer pair in history. Furthermore, to reduce the interference of the irrelevant information in the predicted answer, A-Scorer, an answer scorer is designed to evaluate the confidence of the predicted answer. We conduct a series of experiments on QuAC and CoQA datasets, and the results demonstrate the effectiveness and practicality of our proposed Auto-ACE framework.
%U https://aclanthology.org/2024.sighan-1.9
%P 80-87
Markdown (Informal)
[Auto-ACE: An Automatic Answer Correctness Evaluation Method for Conversational Question Answering](https://aclanthology.org/2024.sighan-1.9) (Bai et al., SIGHAN-WS 2024)
ACL