@inproceedings{li-etal-2020-pgl,
title = "{PGL} at {T}ext{G}raphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods",
author = "Li, Weibin and
Lu, Yuxiang and
Huang, Zhengjie and
Su, Weiyue and
Liu, Jiaxiang and
Feng, Shikun and
Sun, Yu",
editor = "Ustalov, Dmitry and
Somasundaran, Swapna and
Panchenko, Alexander and
Malliaros, Fragkiskos D. and
Hulpu{\textcommabelow{s}}, Ioana and
Jansen, Peter and
Jana, Abhik",
booktitle = "Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.textgraphs-1.11",
doi = "10.18653/v1/2020.textgraphs-1.11",
pages = "98--102",
abstract = "This paper describes the system designed by the Baidu PGL Team which achieved the first place in the TextGraphs 2020 Shared Task. The task focuses on generating explanations for elementary science questions. Given a question and its corresponding correct answer, we are asked to select the facts that can explain why the answer is correct for the question and answering (QA) from a large knowledge base. To address this problem, we use a pre-trained language model to recall the top-K relevant explanations for each question. Then, we adopt a re-ranking approach based on a pre-trained language model to rank the candidate explanations. To further improve the rankings, we also develop an architecture consisting both powerful pre-trained transformers and GNNs to tackle the multi-hop inference problem. The official evaluation shows that, our system can outperform the second best system by 1.91 points.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-pgl">
<titleInfo>
<title>PGL at TextGraphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weibin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxiang</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengjie</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyue</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxiang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikun</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Ustalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swapna</namePart>
<namePart type="family">Somasundaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fragkiskos</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Malliaros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioana</namePart>
<namePart type="family">Hulpu\textcommabelows</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Jansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhik</namePart>
<namePart type="family">Jana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the system designed by the Baidu PGL Team which achieved the first place in the TextGraphs 2020 Shared Task. The task focuses on generating explanations for elementary science questions. Given a question and its corresponding correct answer, we are asked to select the facts that can explain why the answer is correct for the question and answering (QA) from a large knowledge base. To address this problem, we use a pre-trained language model to recall the top-K relevant explanations for each question. Then, we adopt a re-ranking approach based on a pre-trained language model to rank the candidate explanations. To further improve the rankings, we also develop an architecture consisting both powerful pre-trained transformers and GNNs to tackle the multi-hop inference problem. The official evaluation shows that, our system can outperform the second best system by 1.91 points.</abstract>
<identifier type="citekey">li-etal-2020-pgl</identifier>
<identifier type="doi">10.18653/v1/2020.textgraphs-1.11</identifier>
<location>
<url>https://aclanthology.org/2020.textgraphs-1.11</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>98</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PGL at TextGraphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods
%A Li, Weibin
%A Lu, Yuxiang
%A Huang, Zhengjie
%A Su, Weiyue
%A Liu, Jiaxiang
%A Feng, Shikun
%A Sun, Yu
%Y Ustalov, Dmitry
%Y Somasundaran, Swapna
%Y Panchenko, Alexander
%Y Malliaros, Fragkiskos D.
%Y Hulpu\textcommabelows, Ioana
%Y Jansen, Peter
%Y Jana, Abhik
%S Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F li-etal-2020-pgl
%X This paper describes the system designed by the Baidu PGL Team which achieved the first place in the TextGraphs 2020 Shared Task. The task focuses on generating explanations for elementary science questions. Given a question and its corresponding correct answer, we are asked to select the facts that can explain why the answer is correct for the question and answering (QA) from a large knowledge base. To address this problem, we use a pre-trained language model to recall the top-K relevant explanations for each question. Then, we adopt a re-ranking approach based on a pre-trained language model to rank the candidate explanations. To further improve the rankings, we also develop an architecture consisting both powerful pre-trained transformers and GNNs to tackle the multi-hop inference problem. The official evaluation shows that, our system can outperform the second best system by 1.91 points.
%R 10.18653/v1/2020.textgraphs-1.11
%U https://aclanthology.org/2020.textgraphs-1.11
%U https://doi.org/10.18653/v1/2020.textgraphs-1.11
%P 98-102
Markdown (Informal)
[PGL at TextGraphs 2020 Shared Task: Explanation Regeneration using Language and Graph Learning Methods](https://aclanthology.org/2020.textgraphs-1.11) (Li et al., TextGraphs 2020)
ACL