@inproceedings{ma-etal-2022-open,
title = "Open Domain Question Answering with A Unified Knowledge Interface",
author = "Ma, Kaixin and
Cheng, Hao and
Liu, Xiaodong and
Nyberg, Eric and
Gao, Jianfeng",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.113",
doi = "10.18653/v1/2022.acl-long.113",
pages = "1605--1620",
abstract = "The retriever-reader framework is popular for open-domain question answering (ODQA) due to its ability to use explicit knowledge. Although prior work has sought to increase the knowledge coverage by incorporating structured knowledge beyond text, accessing heterogeneous knowledge sources through a unified interface remains an open question. While data-to-text generation has the potential to serve as a universal interface for data and text, its feasibility for downstream tasks remains largely unknown. In this work, we bridge this gap and use the data-to-text method as a means for encoding structured knowledge for open-domain question answering. Specifically, we propose a verbalizer-retriever-reader framework for ODQA over data and text where verbalized tables from Wikipedia and graphs from Wikidata are used as augmented knowledge sources. We show that our Unified Data and Text QA, UDT-QA, can effectively benefit from the expanded knowledge index, leading to large gains over text-only baselines. Notably, our approach sets the single-model state-of-the-art on Natural Questions. Furthermore, our analyses indicate that verbalized knowledge is preferred for answer reasoning for both adapted and hot-swap settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2022-open">
<titleInfo>
<title>Open Domain Question Answering with A Unified Knowledge Interface</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaixin</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Nyberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfeng</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The retriever-reader framework is popular for open-domain question answering (ODQA) due to its ability to use explicit knowledge. Although prior work has sought to increase the knowledge coverage by incorporating structured knowledge beyond text, accessing heterogeneous knowledge sources through a unified interface remains an open question. While data-to-text generation has the potential to serve as a universal interface for data and text, its feasibility for downstream tasks remains largely unknown. In this work, we bridge this gap and use the data-to-text method as a means for encoding structured knowledge for open-domain question answering. Specifically, we propose a verbalizer-retriever-reader framework for ODQA over data and text where verbalized tables from Wikipedia and graphs from Wikidata are used as augmented knowledge sources. We show that our Unified Data and Text QA, UDT-QA, can effectively benefit from the expanded knowledge index, leading to large gains over text-only baselines. Notably, our approach sets the single-model state-of-the-art on Natural Questions. Furthermore, our analyses indicate that verbalized knowledge is preferred for answer reasoning for both adapted and hot-swap settings.</abstract>
<identifier type="citekey">ma-etal-2022-open</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.113</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.113</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1605</start>
<end>1620</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Open Domain Question Answering with A Unified Knowledge Interface
%A Ma, Kaixin
%A Cheng, Hao
%A Liu, Xiaodong
%A Nyberg, Eric
%A Gao, Jianfeng
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F ma-etal-2022-open
%X The retriever-reader framework is popular for open-domain question answering (ODQA) due to its ability to use explicit knowledge. Although prior work has sought to increase the knowledge coverage by incorporating structured knowledge beyond text, accessing heterogeneous knowledge sources through a unified interface remains an open question. While data-to-text generation has the potential to serve as a universal interface for data and text, its feasibility for downstream tasks remains largely unknown. In this work, we bridge this gap and use the data-to-text method as a means for encoding structured knowledge for open-domain question answering. Specifically, we propose a verbalizer-retriever-reader framework for ODQA over data and text where verbalized tables from Wikipedia and graphs from Wikidata are used as augmented knowledge sources. We show that our Unified Data and Text QA, UDT-QA, can effectively benefit from the expanded knowledge index, leading to large gains over text-only baselines. Notably, our approach sets the single-model state-of-the-art on Natural Questions. Furthermore, our analyses indicate that verbalized knowledge is preferred for answer reasoning for both adapted and hot-swap settings.
%R 10.18653/v1/2022.acl-long.113
%U https://aclanthology.org/2022.acl-long.113
%U https://doi.org/10.18653/v1/2022.acl-long.113
%P 1605-1620
Markdown (Informal)
[Open Domain Question Answering with A Unified Knowledge Interface](https://aclanthology.org/2022.acl-long.113) (Ma et al., ACL 2022)
ACL
- Kaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg, and Jianfeng Gao. 2022. Open Domain Question Answering with A Unified Knowledge Interface. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1605–1620, Dublin, Ireland. Association for Computational Linguistics.