@inproceedings{ngonga-ngomo-etal-2018-bengal,
title = "{BENGAL}: An Automatic Benchmark Generator for Entity Recognition and Linking",
author = {Ngonga Ngomo, Axel-Cyrille and
R{\"o}der, Michael and
Moussallem, Diego and
Usbeck, Ricardo and
Speck, Ren{\'e}},
editor = "Krahmer, Emiel and
Gatt, Albert and
Goudbeek, Martijn",
booktitle = "Proceedings of the 11th International Conference on Natural Language Generation",
month = nov,
year = "2018",
address = "Tilburg University, The Netherlands",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6541",
doi = "10.18653/v1/W18-6541",
pages = "339--349",
abstract = "The manual creation of gold standards for named entity recognition and entity linking is time- and resource-intensive. Moreover, recent works show that such gold standards contain a large proportion of mistakes in addition to being difficult to maintain. We hence present Bengal, a novel automatic generation of such gold standards as a complement to manually created benchmarks. The main advantage of our benchmarks is that they can be readily generated at any time. They are also cost-effective while being guaranteed to be free of annotation errors. We compare the performance of 11 tools on benchmarks in English generated by Bengal and on 16 benchmarks created manually. We show that our approach can be ported easily across languages by presenting results achieved by 4 tools on both Brazilian Portuguese and Spanish. Overall, our results suggest that our automatic benchmark generation approach can create varied benchmarks that have characteristics similar to those of existing benchmarks. Our approach is open-source. Our experimental results are available at \url{http://faturl.com/bengalexpinlg} and the code at \url{https://github.com/dice-group/BENGAL}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ngonga-ngomo-etal-2018-bengal">
<titleInfo>
<title>BENGAL: An Automatic Benchmark Generator for Entity Recognition and Linking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Axel-Cyrille</namePart>
<namePart type="family">Ngonga Ngomo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Röder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Moussallem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Usbeck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">René</namePart>
<namePart type="family">Speck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emiel</namePart>
<namePart type="family">Krahmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Gatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martijn</namePart>
<namePart type="family">Goudbeek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tilburg University, The Netherlands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The manual creation of gold standards for named entity recognition and entity linking is time- and resource-intensive. Moreover, recent works show that such gold standards contain a large proportion of mistakes in addition to being difficult to maintain. We hence present Bengal, a novel automatic generation of such gold standards as a complement to manually created benchmarks. The main advantage of our benchmarks is that they can be readily generated at any time. They are also cost-effective while being guaranteed to be free of annotation errors. We compare the performance of 11 tools on benchmarks in English generated by Bengal and on 16 benchmarks created manually. We show that our approach can be ported easily across languages by presenting results achieved by 4 tools on both Brazilian Portuguese and Spanish. Overall, our results suggest that our automatic benchmark generation approach can create varied benchmarks that have characteristics similar to those of existing benchmarks. Our approach is open-source. Our experimental results are available at http://faturl.com/bengalexpinlg and the code at https://github.com/dice-group/BENGAL.</abstract>
<identifier type="citekey">ngonga-ngomo-etal-2018-bengal</identifier>
<identifier type="doi">10.18653/v1/W18-6541</identifier>
<location>
<url>https://aclanthology.org/W18-6541</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>339</start>
<end>349</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BENGAL: An Automatic Benchmark Generator for Entity Recognition and Linking
%A Ngonga Ngomo, Axel-Cyrille
%A Röder, Michael
%A Moussallem, Diego
%A Usbeck, Ricardo
%A Speck, René
%Y Krahmer, Emiel
%Y Gatt, Albert
%Y Goudbeek, Martijn
%S Proceedings of the 11th International Conference on Natural Language Generation
%D 2018
%8 November
%I Association for Computational Linguistics
%C Tilburg University, The Netherlands
%F ngonga-ngomo-etal-2018-bengal
%X The manual creation of gold standards for named entity recognition and entity linking is time- and resource-intensive. Moreover, recent works show that such gold standards contain a large proportion of mistakes in addition to being difficult to maintain. We hence present Bengal, a novel automatic generation of such gold standards as a complement to manually created benchmarks. The main advantage of our benchmarks is that they can be readily generated at any time. They are also cost-effective while being guaranteed to be free of annotation errors. We compare the performance of 11 tools on benchmarks in English generated by Bengal and on 16 benchmarks created manually. We show that our approach can be ported easily across languages by presenting results achieved by 4 tools on both Brazilian Portuguese and Spanish. Overall, our results suggest that our automatic benchmark generation approach can create varied benchmarks that have characteristics similar to those of existing benchmarks. Our approach is open-source. Our experimental results are available at http://faturl.com/bengalexpinlg and the code at https://github.com/dice-group/BENGAL.
%R 10.18653/v1/W18-6541
%U https://aclanthology.org/W18-6541
%U https://doi.org/10.18653/v1/W18-6541
%P 339-349
Markdown (Informal)
[BENGAL: An Automatic Benchmark Generator for Entity Recognition and Linking](https://aclanthology.org/W18-6541) (Ngonga Ngomo et al., INLG 2018)
ACL