@inproceedings{otrusina-smrz-2016-wtf,
title = "{WTF}-{LOD} - A New Resource for Large-Scale {NER} Evaluation",
author = "Otrusina, Lubomir and
Smrz, Pavel",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1525/",
pages = "3299--3302",
abstract = "This paper introduces the Web TextFull linkage to Linked Open Data (WTF-LOD) dataset intended for large-scale evaluation of named entity recognition (NER) systems. First, we present the process of collecting data from the largest publically-available textual corpora, including Wikipedia dumps, monthly runs of the CommonCrawl, and ClueWeb09/12. We discuss similarities and differences of related initiatives such as WikiLinks and WikiReverse. Our work primarily focuses on links from ``textfull'' documents (links surrounded by a text that provides a useful context for entity linking), de-duplication of the data and advanced cleaning procedures. Presented statistics demonstrate that the collected data forms one of the largest available resource of its kind. They also prove suitability of the result for complex NER evaluation campaigns, including an analysis of the most ambiguous name mentions appearing in the data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="otrusina-smrz-2016-wtf">
<titleInfo>
<title>WTF-LOD - A New Resource for Large-Scale NER Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lubomir</namePart>
<namePart type="family">Otrusina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Smrz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces the Web TextFull linkage to Linked Open Data (WTF-LOD) dataset intended for large-scale evaluation of named entity recognition (NER) systems. First, we present the process of collecting data from the largest publically-available textual corpora, including Wikipedia dumps, monthly runs of the CommonCrawl, and ClueWeb09/12. We discuss similarities and differences of related initiatives such as WikiLinks and WikiReverse. Our work primarily focuses on links from “textfull” documents (links surrounded by a text that provides a useful context for entity linking), de-duplication of the data and advanced cleaning procedures. Presented statistics demonstrate that the collected data forms one of the largest available resource of its kind. They also prove suitability of the result for complex NER evaluation campaigns, including an analysis of the most ambiguous name mentions appearing in the data.</abstract>
<identifier type="citekey">otrusina-smrz-2016-wtf</identifier>
<location>
<url>https://aclanthology.org/L16-1525/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3299</start>
<end>3302</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WTF-LOD - A New Resource for Large-Scale NER Evaluation
%A Otrusina, Lubomir
%A Smrz, Pavel
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F otrusina-smrz-2016-wtf
%X This paper introduces the Web TextFull linkage to Linked Open Data (WTF-LOD) dataset intended for large-scale evaluation of named entity recognition (NER) systems. First, we present the process of collecting data from the largest publically-available textual corpora, including Wikipedia dumps, monthly runs of the CommonCrawl, and ClueWeb09/12. We discuss similarities and differences of related initiatives such as WikiLinks and WikiReverse. Our work primarily focuses on links from “textfull” documents (links surrounded by a text that provides a useful context for entity linking), de-duplication of the data and advanced cleaning procedures. Presented statistics demonstrate that the collected data forms one of the largest available resource of its kind. They also prove suitability of the result for complex NER evaluation campaigns, including an analysis of the most ambiguous name mentions appearing in the data.
%U https://aclanthology.org/L16-1525/
%P 3299-3302
Markdown (Informal)
[WTF-LOD - A New Resource for Large-Scale NER Evaluation](https://aclanthology.org/L16-1525/) (Otrusina & Smrz, LREC 2016)
ACL
- Lubomir Otrusina and Pavel Smrz. 2016. WTF-LOD - A New Resource for Large-Scale NER Evaluation. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3299–3302, Portorož, Slovenia. European Language Resources Association (ELRA).