@inproceedings{li-etal-2023-interview,
title = "Interview Evaluation: A Novel Approach for Automatic Evaluation of Conversational Question Answering Models",
author = "Li, Xibo and
Zou, Bowei and
Fan, Yifan and
Li, Yanling and
Aw, Ai Ti and
Hong, Yu",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.209",
doi = "10.18653/v1/2023.emnlp-main.209",
pages = "3435--3446",
abstract = "Conversational Question Answering (CQA) aims to provide natural language answers to users in information-seeking dialogues. Existing CQA benchmarks often evaluate models using pre-collected human-human conversations. However, replacing the model-predicted dialogue history with ground truth compromises the naturalness and sustainability of CQA evaluation. While previous studies proposed using predicted history and rewriting techniques to address unresolved coreferences and incoherencies, this approach renders the question self-contained from the conversation. In this paper, we propose a novel automatic evaluation approach, interview evaluation. Specifically, ChatGPT acts as the interviewer (Q agent) with a set of carefully designed prompts, and the CQA model under test serves as the interviewee (A agent). During the interview evaluation, questions are dynamically generated by the Q agent to guide the A agent in predicting the correct answer through an interactive process. We evaluated four different models on QuAC and two models on CoQA in our experiments. The experiment results demonstrate that our interview evaluation has advantages over previous CQA evaluation approaches, particularly in terms of naturalness and coherence. The source code is made publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-interview">
<titleInfo>
<title>Interview Evaluation: A Novel Approach for Automatic Evaluation of Conversational Question Answering Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xibo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowei</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ai</namePart>
<namePart type="given">Ti</namePart>
<namePart type="family">Aw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conversational Question Answering (CQA) aims to provide natural language answers to users in information-seeking dialogues. Existing CQA benchmarks often evaluate models using pre-collected human-human conversations. However, replacing the model-predicted dialogue history with ground truth compromises the naturalness and sustainability of CQA evaluation. While previous studies proposed using predicted history and rewriting techniques to address unresolved coreferences and incoherencies, this approach renders the question self-contained from the conversation. In this paper, we propose a novel automatic evaluation approach, interview evaluation. Specifically, ChatGPT acts as the interviewer (Q agent) with a set of carefully designed prompts, and the CQA model under test serves as the interviewee (A agent). During the interview evaluation, questions are dynamically generated by the Q agent to guide the A agent in predicting the correct answer through an interactive process. We evaluated four different models on QuAC and two models on CoQA in our experiments. The experiment results demonstrate that our interview evaluation has advantages over previous CQA evaluation approaches, particularly in terms of naturalness and coherence. The source code is made publicly available.</abstract>
<identifier type="citekey">li-etal-2023-interview</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.209</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.209</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>3435</start>
<end>3446</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interview Evaluation: A Novel Approach for Automatic Evaluation of Conversational Question Answering Models
%A Li, Xibo
%A Zou, Bowei
%A Fan, Yifan
%A Li, Yanling
%A Aw, Ai Ti
%A Hong, Yu
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F li-etal-2023-interview
%X Conversational Question Answering (CQA) aims to provide natural language answers to users in information-seeking dialogues. Existing CQA benchmarks often evaluate models using pre-collected human-human conversations. However, replacing the model-predicted dialogue history with ground truth compromises the naturalness and sustainability of CQA evaluation. While previous studies proposed using predicted history and rewriting techniques to address unresolved coreferences and incoherencies, this approach renders the question self-contained from the conversation. In this paper, we propose a novel automatic evaluation approach, interview evaluation. Specifically, ChatGPT acts as the interviewer (Q agent) with a set of carefully designed prompts, and the CQA model under test serves as the interviewee (A agent). During the interview evaluation, questions are dynamically generated by the Q agent to guide the A agent in predicting the correct answer through an interactive process. We evaluated four different models on QuAC and two models on CoQA in our experiments. The experiment results demonstrate that our interview evaluation has advantages over previous CQA evaluation approaches, particularly in terms of naturalness and coherence. The source code is made publicly available.
%R 10.18653/v1/2023.emnlp-main.209
%U https://aclanthology.org/2023.emnlp-main.209
%U https://doi.org/10.18653/v1/2023.emnlp-main.209
%P 3435-3446
Markdown (Informal)
[Interview Evaluation: A Novel Approach for Automatic Evaluation of Conversational Question Answering Models](https://aclanthology.org/2023.emnlp-main.209) (Li et al., EMNLP 2023)
ACL