@inproceedings{bolotova-baranova-etal-2023-wikihowqa,
title = "{W}iki{H}ow{QA}: A Comprehensive Benchmark for Multi-Document Non-Factoid Question Answering",
author = "Bolotova-Baranova, Valeriia and
Blinov, Vladislav and
Filippova, Sofya and
Scholer, Falk and
Sanderson, Mark",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.290/",
doi = "10.18653/v1/2023.acl-long.290",
pages = "5291--5314",
abstract = "Answering non-factoid questions (NFQA) is a challenging task, requiring passage-level answers that are difficult to construct and evaluate. Search engines may provide a summary of a single web page, but many questions require reasoning across multiple documents. Meanwhile, modern models can generate highly coherent and fluent, but often factually incorrect answers that can deceive even non-expert humans. There is a critical need for high-quality resources for multi-document NFQA (MD-NFQA) to train new models and evaluate answers' grounding and factual consistency in relation to supporting documents. To address this gap, we introduce WikiHowQA, a new multi-document NFQA benchmark built on WikiHow, a website dedicated to answering {\textquotedblleft}how-to{\textquotedblright} questions. The benchmark includes 11,746 human-written answers along with 74,527 supporting documents. We describe the unique challenges of the resource, provide strong baselines, and propose a novel human evaluation framework that utilizes highlighted relevant supporting passages to mitigate issues such as assessor unfamiliarity with the question topic. All code and data, including the automatic code for preparing the human evaluation, are publicly available."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bolotova-baranova-etal-2023-wikihowqa">
<titleInfo>
<title>WikiHowQA: A Comprehensive Benchmark for Multi-Document Non-Factoid Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valeriia</namePart>
<namePart type="family">Bolotova-Baranova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Blinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sofya</namePart>
<namePart type="family">Filippova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Falk</namePart>
<namePart type="family">Scholer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Sanderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Answering non-factoid questions (NFQA) is a challenging task, requiring passage-level answers that are difficult to construct and evaluate. Search engines may provide a summary of a single web page, but many questions require reasoning across multiple documents. Meanwhile, modern models can generate highly coherent and fluent, but often factually incorrect answers that can deceive even non-expert humans. There is a critical need for high-quality resources for multi-document NFQA (MD-NFQA) to train new models and evaluate answers’ grounding and factual consistency in relation to supporting documents. To address this gap, we introduce WikiHowQA, a new multi-document NFQA benchmark built on WikiHow, a website dedicated to answering “how-to” questions. The benchmark includes 11,746 human-written answers along with 74,527 supporting documents. We describe the unique challenges of the resource, provide strong baselines, and propose a novel human evaluation framework that utilizes highlighted relevant supporting passages to mitigate issues such as assessor unfamiliarity with the question topic. All code and data, including the automatic code for preparing the human evaluation, are publicly available.</abstract>
<identifier type="citekey">bolotova-baranova-etal-2023-wikihowqa</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.290</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.290/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>5291</start>
<end>5314</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WikiHowQA: A Comprehensive Benchmark for Multi-Document Non-Factoid Question Answering
%A Bolotova-Baranova, Valeriia
%A Blinov, Vladislav
%A Filippova, Sofya
%A Scholer, Falk
%A Sanderson, Mark
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F bolotova-baranova-etal-2023-wikihowqa
%X Answering non-factoid questions (NFQA) is a challenging task, requiring passage-level answers that are difficult to construct and evaluate. Search engines may provide a summary of a single web page, but many questions require reasoning across multiple documents. Meanwhile, modern models can generate highly coherent and fluent, but often factually incorrect answers that can deceive even non-expert humans. There is a critical need for high-quality resources for multi-document NFQA (MD-NFQA) to train new models and evaluate answers’ grounding and factual consistency in relation to supporting documents. To address this gap, we introduce WikiHowQA, a new multi-document NFQA benchmark built on WikiHow, a website dedicated to answering “how-to” questions. The benchmark includes 11,746 human-written answers along with 74,527 supporting documents. We describe the unique challenges of the resource, provide strong baselines, and propose a novel human evaluation framework that utilizes highlighted relevant supporting passages to mitigate issues such as assessor unfamiliarity with the question topic. All code and data, including the automatic code for preparing the human evaluation, are publicly available.
%R 10.18653/v1/2023.acl-long.290
%U https://aclanthology.org/2023.acl-long.290/
%U https://doi.org/10.18653/v1/2023.acl-long.290
%P 5291-5314
Markdown (Informal)
[WikiHowQA: A Comprehensive Benchmark for Multi-Document Non-Factoid Question Answering](https://aclanthology.org/2023.acl-long.290/) (Bolotova-Baranova et al., ACL 2023)
ACL