@inproceedings{ma-etal-2022-open-domain,
title = "Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge",
author = "Ma, Kaixin and
Cheng, Hao and
Liu, Xiaodong and
Nyberg, Eric and
Gao, Jianfeng",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.392",
doi = "10.18653/v1/2022.findings-emnlp.392",
pages = "5360--5374",
abstract = "We propose a novel open-domain question answering (ODQA) framework for answering single/multi-hop questions across heterogeneous knowledge sources.The key novelty of our method is the introduction of the intermediary modules into the current retriever-reader pipeline.Unlike previous methods that solely rely on the retriever for gathering all evidence in isolation,our intermediary performs a chain of reasoning over the retrieved set.Specifically, our method links the retrieved evidence with its related global context into graphs and organizes them into a candidate list of evidence chains.Built upon pretrained language models, our system achieves competitive performance on two ODQA datasets, OTT-QA and NQ, against tables and passages from Wikipedia.In particular, our model substantially outperforms the previous state-of-the-art on OTT-QA with an exact match score of 47.3 (45{\%} relative gain).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2022-open-domain">
<titleInfo>
<title>Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge</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>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a novel open-domain question answering (ODQA) framework for answering single/multi-hop questions across heterogeneous knowledge sources.The key novelty of our method is the introduction of the intermediary modules into the current retriever-reader pipeline.Unlike previous methods that solely rely on the retriever for gathering all evidence in isolation,our intermediary performs a chain of reasoning over the retrieved set.Specifically, our method links the retrieved evidence with its related global context into graphs and organizes them into a candidate list of evidence chains.Built upon pretrained language models, our system achieves competitive performance on two ODQA datasets, OTT-QA and NQ, against tables and passages from Wikipedia.In particular, our model substantially outperforms the previous state-of-the-art on OTT-QA with an exact match score of 47.3 (45% relative gain).</abstract>
<identifier type="citekey">ma-etal-2022-open-domain</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.392</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.392</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>5360</start>
<end>5374</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge
%A Ma, Kaixin
%A Cheng, Hao
%A Liu, Xiaodong
%A Nyberg, Eric
%A Gao, Jianfeng
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F ma-etal-2022-open-domain
%X We propose a novel open-domain question answering (ODQA) framework for answering single/multi-hop questions across heterogeneous knowledge sources.The key novelty of our method is the introduction of the intermediary modules into the current retriever-reader pipeline.Unlike previous methods that solely rely on the retriever for gathering all evidence in isolation,our intermediary performs a chain of reasoning over the retrieved set.Specifically, our method links the retrieved evidence with its related global context into graphs and organizes them into a candidate list of evidence chains.Built upon pretrained language models, our system achieves competitive performance on two ODQA datasets, OTT-QA and NQ, against tables and passages from Wikipedia.In particular, our model substantially outperforms the previous state-of-the-art on OTT-QA with an exact match score of 47.3 (45% relative gain).
%R 10.18653/v1/2022.findings-emnlp.392
%U https://aclanthology.org/2022.findings-emnlp.392
%U https://doi.org/10.18653/v1/2022.findings-emnlp.392
%P 5360-5374
Markdown (Informal)
[Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge](https://aclanthology.org/2022.findings-emnlp.392) (Ma et al., Findings 2022)
ACL