@inproceedings{guo-etal-2021-multireqa,
title = "{M}ulti{R}e{QA}: A Cross-Domain Evaluation for{R}etrieval Question Answering Models",
author = "Guo, Mandy and
Yang, Yinfei and
Cer, Daniel and
Shen, Qinlan and
Constant, Noah",
booktitle = "Proceedings of the Second Workshop on Domain Adaptation for NLP",
month = apr,
year = "2021",
address = "Kyiv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.adaptnlp-1.10",
pages = "94--104",
abstract = "Retrieval question answering (ReQA) is the task of retrieving a sentence-level answer to a question from an open corpus (Ahmad et al.,2019).This dataset paper presents MultiReQA, a new multi-domain ReQA evaluation suite composed of eight retrieval QA tasks drawn from publicly available QA datasets. We explore systematic retrieval based evaluation and transfer learning across domains over these datasets using a number of strong base-lines including two supervised neural models, based on fine-tuning BERT and USE-QA models respectively, as well as a surprisingly effective information retrieval baseline, BM25. Five of these tasks contain both training and test data, while three contain test data only. Performing cross training on the five tasks with training data shows that while a general model covering all domains is achievable, the best performance is often obtained by training exclusively on in-domain data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2021-multireqa">
<titleInfo>
<title>MultiReQA: A Cross-Domain Evaluation forRetrieval Question Answering Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mandy</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinfei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Cer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qinlan</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="family">Constant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-apr</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Domain Adaptation for NLP</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Retrieval question answering (ReQA) is the task of retrieving a sentence-level answer to a question from an open corpus (Ahmad et al.,2019).This dataset paper presents MultiReQA, a new multi-domain ReQA evaluation suite composed of eight retrieval QA tasks drawn from publicly available QA datasets. We explore systematic retrieval based evaluation and transfer learning across domains over these datasets using a number of strong base-lines including two supervised neural models, based on fine-tuning BERT and USE-QA models respectively, as well as a surprisingly effective information retrieval baseline, BM25. Five of these tasks contain both training and test data, while three contain test data only. Performing cross training on the five tasks with training data shows that while a general model covering all domains is achievable, the best performance is often obtained by training exclusively on in-domain data.</abstract>
<identifier type="citekey">guo-etal-2021-multireqa</identifier>
<location>
<url>https://aclanthology.org/2021.adaptnlp-1.10</url>
</location>
<part>
<date>2021-apr</date>
<extent unit="page">
<start>94</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiReQA: A Cross-Domain Evaluation forRetrieval Question Answering Models
%A Guo, Mandy
%A Yang, Yinfei
%A Cer, Daniel
%A Shen, Qinlan
%A Constant, Noah
%S Proceedings of the Second Workshop on Domain Adaptation for NLP
%D 2021
%8 apr
%I Association for Computational Linguistics
%C Kyiv, Ukraine
%F guo-etal-2021-multireqa
%X Retrieval question answering (ReQA) is the task of retrieving a sentence-level answer to a question from an open corpus (Ahmad et al.,2019).This dataset paper presents MultiReQA, a new multi-domain ReQA evaluation suite composed of eight retrieval QA tasks drawn from publicly available QA datasets. We explore systematic retrieval based evaluation and transfer learning across domains over these datasets using a number of strong base-lines including two supervised neural models, based on fine-tuning BERT and USE-QA models respectively, as well as a surprisingly effective information retrieval baseline, BM25. Five of these tasks contain both training and test data, while three contain test data only. Performing cross training on the five tasks with training data shows that while a general model covering all domains is achievable, the best performance is often obtained by training exclusively on in-domain data.
%U https://aclanthology.org/2021.adaptnlp-1.10
%P 94-104
Markdown (Informal)
[MultiReQA: A Cross-Domain Evaluation forRetrieval Question Answering Models](https://aclanthology.org/2021.adaptnlp-1.10) (Guo et al., AdaptNLP 2021)
ACL