@inproceedings{zhang-etal-2020-graph,
title = "A Graph Representation of Semi-structured Data for Web Question Answering",
author = "Zhang, Xingyao and
Shou, Linjun and
Pei, Jian and
Gong, Ming and
Wen, Lijie and
Jiang, Daxin",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.5",
doi = "10.18653/v1/2020.coling-main.5",
pages = "51--61",
abstract = "The abundant semi-structured data on the Web, such as HTML-based tables and lists, provide commercial search engines a rich information source for question answering (QA). Different from plain text passages in Web documents, Web tables and lists have inherent structures, which carry semantic correlations among various elements in tables and lists. Many existing studies treat tables and lists as flat documents with pieces of text and do not make good use of semantic information hidden in structures. In this paper, we propose a novel graph representation of Web tables and lists based on a systematic categorization of the components in semi-structured data as well as their relations. We also develop pre-training and reasoning techniques on the graph model for the QA task. Extensive experiments on several real datasets collected from a commercial engine verify the effectiveness of our approach. Our method improves F1 score by 3.90 points over the state-of-the-art baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2020-graph">
<titleInfo>
<title>A Graph Representation of Semi-structured Data for Web Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xingyao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linjun</namePart>
<namePart type="family">Shou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Pei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lijie</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daxin</namePart>
<namePart type="family">Jiang</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 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The abundant semi-structured data on the Web, such as HTML-based tables and lists, provide commercial search engines a rich information source for question answering (QA). Different from plain text passages in Web documents, Web tables and lists have inherent structures, which carry semantic correlations among various elements in tables and lists. Many existing studies treat tables and lists as flat documents with pieces of text and do not make good use of semantic information hidden in structures. In this paper, we propose a novel graph representation of Web tables and lists based on a systematic categorization of the components in semi-structured data as well as their relations. We also develop pre-training and reasoning techniques on the graph model for the QA task. Extensive experiments on several real datasets collected from a commercial engine verify the effectiveness of our approach. Our method improves F1 score by 3.90 points over the state-of-the-art baselines.</abstract>
<identifier type="citekey">zhang-etal-2020-graph</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.5</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.5</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>51</start>
<end>61</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Graph Representation of Semi-structured Data for Web Question Answering
%A Zhang, Xingyao
%A Shou, Linjun
%A Pei, Jian
%A Gong, Ming
%A Wen, Lijie
%A Jiang, Daxin
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F zhang-etal-2020-graph
%X The abundant semi-structured data on the Web, such as HTML-based tables and lists, provide commercial search engines a rich information source for question answering (QA). Different from plain text passages in Web documents, Web tables and lists have inherent structures, which carry semantic correlations among various elements in tables and lists. Many existing studies treat tables and lists as flat documents with pieces of text and do not make good use of semantic information hidden in structures. In this paper, we propose a novel graph representation of Web tables and lists based on a systematic categorization of the components in semi-structured data as well as their relations. We also develop pre-training and reasoning techniques on the graph model for the QA task. Extensive experiments on several real datasets collected from a commercial engine verify the effectiveness of our approach. Our method improves F1 score by 3.90 points over the state-of-the-art baselines.
%R 10.18653/v1/2020.coling-main.5
%U https://aclanthology.org/2020.coling-main.5
%U https://doi.org/10.18653/v1/2020.coling-main.5
%P 51-61
Markdown (Informal)
[A Graph Representation of Semi-structured Data for Web Question Answering](https://aclanthology.org/2020.coling-main.5) (Zhang et al., COLING 2020)
ACL