@inproceedings{rodriguez-boyd-graber-2021-evaluation,
title = "Evaluation Paradigms in Question Answering",
author = "Rodriguez, Pedro and
Boyd-Graber, Jordan",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.758",
doi = "10.18653/v1/2021.emnlp-main.758",
pages = "9630--9642",
abstract = "Question answering (QA) primarily descends from two branches of research: (1) Alan Turing{'}s investigation of machine intelligence at Manchester University and (2) Cyril Cleverdon{'}s comparison of library card catalog indices at Cranfield University. This position paper names and distinguishes these paradigms. Despite substantial overlap, subtle but significant distinctions exert an outsize influence on research. While one evaluation paradigm values creating more intelligent QA systems, the other paradigm values building QA systems that appeal to users. By better understanding the epistemic heritage of QA, researchers, academia, and industry can more effectively accelerate QA research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rodriguez-boyd-graber-2021-evaluation">
<titleInfo>
<title>Evaluation Paradigms in Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Question answering (QA) primarily descends from two branches of research: (1) Alan Turing’s investigation of machine intelligence at Manchester University and (2) Cyril Cleverdon’s comparison of library card catalog indices at Cranfield University. This position paper names and distinguishes these paradigms. Despite substantial overlap, subtle but significant distinctions exert an outsize influence on research. While one evaluation paradigm values creating more intelligent QA systems, the other paradigm values building QA systems that appeal to users. By better understanding the epistemic heritage of QA, researchers, academia, and industry can more effectively accelerate QA research.</abstract>
<identifier type="citekey">rodriguez-boyd-graber-2021-evaluation</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.758</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.758</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>9630</start>
<end>9642</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation Paradigms in Question Answering
%A Rodriguez, Pedro
%A Boyd-Graber, Jordan
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F rodriguez-boyd-graber-2021-evaluation
%X Question answering (QA) primarily descends from two branches of research: (1) Alan Turing’s investigation of machine intelligence at Manchester University and (2) Cyril Cleverdon’s comparison of library card catalog indices at Cranfield University. This position paper names and distinguishes these paradigms. Despite substantial overlap, subtle but significant distinctions exert an outsize influence on research. While one evaluation paradigm values creating more intelligent QA systems, the other paradigm values building QA systems that appeal to users. By better understanding the epistemic heritage of QA, researchers, academia, and industry can more effectively accelerate QA research.
%R 10.18653/v1/2021.emnlp-main.758
%U https://aclanthology.org/2021.emnlp-main.758
%U https://doi.org/10.18653/v1/2021.emnlp-main.758
%P 9630-9642
Markdown (Informal)
[Evaluation Paradigms in Question Answering](https://aclanthology.org/2021.emnlp-main.758) (Rodriguez & Boyd-Graber, EMNLP 2021)
ACL
- Pedro Rodriguez and Jordan Boyd-Graber. 2021. Evaluation Paradigms in Question Answering. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9630–9642, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.