@inproceedings{qasemizadeh-schumann-2016-acl,
title = "The {ACL} {RD}-{TEC} 2.0: A Language Resource for Evaluating Term Extraction and Entity Recognition Methods",
author = "QasemiZadeh, Behrang and
Schumann, Anne-Kathrin",
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/L16-1294",
pages = "1862--1868",
abstract = "This paper introduces the ACL Reference Dataset for Terminology Extraction and Classification, version 2.0 (ACL RD-TEC 2.0). The ACL RD-TEC 2.0 has been developed with the aim of providing a benchmark for the evaluation of term and entity recognition tasks based on specialised text from the computational linguistics domain. This release of the corpus consists of 300 abstracts from articles in the ACL Anthology Reference Corpus, published between 1978{--}2006. In these abstracts, terms (i.e., single or multi-word lexical units with a specialised meaning) are manually annotated. In addition to their boundaries in running text, annotated terms are classified into one of the seven categories method, tool, language resource (LR), LR product, model, measures and measurements, and other. To assess the quality of the annotations and to determine the difficulty of this annotation task, more than 171 of the abstracts are annotated twice, independently, by each of the two annotators. In total, 6,818 terms are identified and annotated in more than 1300 sentences, resulting in a specialised vocabulary made of 3,318 lexical forms, mapped to 3,471 concepts. We explain the development of the annotation guidelines and discuss some of the challenges we encountered in this annotation task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qasemizadeh-schumann-2016-acl">
<titleInfo>
<title>The ACL RD-TEC 2.0: A Language Resource for Evaluating Term Extraction and Entity Recognition Methods</title>
</titleInfo>
<name type="personal">
<namePart type="given">Behrang</namePart>
<namePart type="family">QasemiZadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Kathrin</namePart>
<namePart type="family">Schumann</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 ACL Reference Dataset for Terminology Extraction and Classification, version 2.0 (ACL RD-TEC 2.0). The ACL RD-TEC 2.0 has been developed with the aim of providing a benchmark for the evaluation of term and entity recognition tasks based on specialised text from the computational linguistics domain. This release of the corpus consists of 300 abstracts from articles in the ACL Anthology Reference Corpus, published between 1978–2006. In these abstracts, terms (i.e., single or multi-word lexical units with a specialised meaning) are manually annotated. In addition to their boundaries in running text, annotated terms are classified into one of the seven categories method, tool, language resource (LR), LR product, model, measures and measurements, and other. To assess the quality of the annotations and to determine the difficulty of this annotation task, more than 171 of the abstracts are annotated twice, independently, by each of the two annotators. In total, 6,818 terms are identified and annotated in more than 1300 sentences, resulting in a specialised vocabulary made of 3,318 lexical forms, mapped to 3,471 concepts. We explain the development of the annotation guidelines and discuss some of the challenges we encountered in this annotation task.</abstract>
<identifier type="citekey">qasemizadeh-schumann-2016-acl</identifier>
<location>
<url>https://aclanthology.org/L16-1294</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1862</start>
<end>1868</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The ACL RD-TEC 2.0: A Language Resource for Evaluating Term Extraction and Entity Recognition Methods
%A QasemiZadeh, Behrang
%A Schumann, Anne-Kathrin
%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 qasemizadeh-schumann-2016-acl
%X This paper introduces the ACL Reference Dataset for Terminology Extraction and Classification, version 2.0 (ACL RD-TEC 2.0). The ACL RD-TEC 2.0 has been developed with the aim of providing a benchmark for the evaluation of term and entity recognition tasks based on specialised text from the computational linguistics domain. This release of the corpus consists of 300 abstracts from articles in the ACL Anthology Reference Corpus, published between 1978–2006. In these abstracts, terms (i.e., single or multi-word lexical units with a specialised meaning) are manually annotated. In addition to their boundaries in running text, annotated terms are classified into one of the seven categories method, tool, language resource (LR), LR product, model, measures and measurements, and other. To assess the quality of the annotations and to determine the difficulty of this annotation task, more than 171 of the abstracts are annotated twice, independently, by each of the two annotators. In total, 6,818 terms are identified and annotated in more than 1300 sentences, resulting in a specialised vocabulary made of 3,318 lexical forms, mapped to 3,471 concepts. We explain the development of the annotation guidelines and discuss some of the challenges we encountered in this annotation task.
%U https://aclanthology.org/L16-1294
%P 1862-1868
Markdown (Informal)
[The ACL RD-TEC 2.0: A Language Resource for Evaluating Term Extraction and Entity Recognition Methods](https://aclanthology.org/L16-1294) (QasemiZadeh & Schumann, LREC 2016)
ACL