@inproceedings{hernandez-gonzalez-etal-2017-merging,
title = "Merging knowledge bases in different languages",
author = "Hern{\'a}ndez-Gonz{\'a}lez, Jer{\'o}nimo and
Hruschka Jr., Estevam R. and
Mitchell, Tom M.",
editor = "Riedl, Martin and
Somasundaran, Swapna and
Glava{\v{s}}, Goran and
Hovy, Eduard",
booktitle = "Proceedings of {T}ext{G}raphs-11: the Workshop on Graph-based Methods for Natural Language Processing",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2403",
doi = "10.18653/v1/W17-2403",
pages = "21--29",
abstract = "Recently, different systems which learn to populate and extend a knowledge base (KB) from the web in different languages have been presented. Although a large set of concepts should be learnt independently from the language used to read, there are facts which are expected to be more easily gathered in local language (e.g., culture or geography). A system that merges KBs learnt in different languages will benefit from the complementary information as long as common beliefs are identified, as well as from redundancy present in web pages written in different languages. In this paper, we deal with the problem of identifying equivalent beliefs (or concepts) across language specific KBs, assuming that they share the same ontology of categories and relations. In a case study with two KBs independently learnt from different inputs, namely web pages written in English and web pages written in Portuguese respectively, we report on the results of two methodologies: an approach based on personalized PageRank and an inference technique to find out common relevant paths through the KBs. The proposed inference technique efficiently identifies relevant paths, outperforming the baseline (a dictionary-based classifier) in the vast majority of tested categories.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hernandez-gonzalez-etal-2017-merging">
<titleInfo>
<title>Merging knowledge bases in different languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jerónimo</namePart>
<namePart type="family">Hernández-González</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Estevam</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Hruschka Jr.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mitchell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of TextGraphs-11: the Workshop on Graph-based Methods for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Riedl</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">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, different systems which learn to populate and extend a knowledge base (KB) from the web in different languages have been presented. Although a large set of concepts should be learnt independently from the language used to read, there are facts which are expected to be more easily gathered in local language (e.g., culture or geography). A system that merges KBs learnt in different languages will benefit from the complementary information as long as common beliefs are identified, as well as from redundancy present in web pages written in different languages. In this paper, we deal with the problem of identifying equivalent beliefs (or concepts) across language specific KBs, assuming that they share the same ontology of categories and relations. In a case study with two KBs independently learnt from different inputs, namely web pages written in English and web pages written in Portuguese respectively, we report on the results of two methodologies: an approach based on personalized PageRank and an inference technique to find out common relevant paths through the KBs. The proposed inference technique efficiently identifies relevant paths, outperforming the baseline (a dictionary-based classifier) in the vast majority of tested categories.</abstract>
<identifier type="citekey">hernandez-gonzalez-etal-2017-merging</identifier>
<identifier type="doi">10.18653/v1/W17-2403</identifier>
<location>
<url>https://aclanthology.org/W17-2403</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>21</start>
<end>29</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Merging knowledge bases in different languages
%A Hernández-González, Jerónimo
%A Hruschka Jr., Estevam R.
%A Mitchell, Tom M.
%Y Riedl, Martin
%Y Somasundaran, Swapna
%Y Glavaš, Goran
%Y Hovy, Eduard
%S Proceedings of TextGraphs-11: the Workshop on Graph-based Methods for Natural Language Processing
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F hernandez-gonzalez-etal-2017-merging
%X Recently, different systems which learn to populate and extend a knowledge base (KB) from the web in different languages have been presented. Although a large set of concepts should be learnt independently from the language used to read, there are facts which are expected to be more easily gathered in local language (e.g., culture or geography). A system that merges KBs learnt in different languages will benefit from the complementary information as long as common beliefs are identified, as well as from redundancy present in web pages written in different languages. In this paper, we deal with the problem of identifying equivalent beliefs (or concepts) across language specific KBs, assuming that they share the same ontology of categories and relations. In a case study with two KBs independently learnt from different inputs, namely web pages written in English and web pages written in Portuguese respectively, we report on the results of two methodologies: an approach based on personalized PageRank and an inference technique to find out common relevant paths through the KBs. The proposed inference technique efficiently identifies relevant paths, outperforming the baseline (a dictionary-based classifier) in the vast majority of tested categories.
%R 10.18653/v1/W17-2403
%U https://aclanthology.org/W17-2403
%U https://doi.org/10.18653/v1/W17-2403
%P 21-29
Markdown (Informal)
[Merging knowledge bases in different languages](https://aclanthology.org/W17-2403) (Hernández-González et al., TextGraphs 2017)
ACL
- Jerónimo Hernández-González, Estevam R. Hruschka Jr., and Tom M. Mitchell. 2017. Merging knowledge bases in different languages. In Proceedings of TextGraphs-11: the Workshop on Graph-based Methods for Natural Language Processing, pages 21–29, Vancouver, Canada. Association for Computational Linguistics.