@inproceedings{hongchao-etal-2016-evalution,
title = "{EVAL}ution-{MAN}: A {C}hinese Dataset for the Training and Evaluation of {DSM}s",
author = "Hongchao, Liu and
Neergaard, Karl and
Santus, Enrico and
Huang, Chu-Ren",
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/L16-1726",
pages = "4583--4587",
abstract = "Distributional semantic models (DSMs) are currently being used in the measurement of word relatedness and word similarity. One shortcoming of DSMs is that they do not provide a principled way to discriminate different semantic relations. Several approaches have been adopted that rely on annotated data either in the training of the model or later in its evaluation. In this paper, we introduce a dataset for training and evaluating DSMs on semantic relations discrimination between words, in Mandarin, Chinese. The construction of the dataset followed EVALution 1.0, which is an English dataset for the training and evaluating of DSMs. The dataset contains 360 relation pairs, distributed in five different semantic relations, including antonymy, synonymy, hypernymy, meronymy and nearsynonymy. All relation pairs were checked manually to estimate their quality. In the 360 word relation pairs, there are 373 relata. They were all extracted and subsequently manually tagged according to their semantic type. The relatas{'} frequency was calculated in a combined corpus of Sinica and Chinese Gigaword. To the best of our knowledge, EVALution-MAN is the first of its kind for Mandarin, Chinese.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hongchao-etal-2016-evalution">
<titleInfo>
<title>EVALution-MAN: A Chinese Dataset for the Training and Evaluation of DSMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Hongchao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karl</namePart>
<namePart type="family">Neergaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</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>Distributional semantic models (DSMs) are currently being used in the measurement of word relatedness and word similarity. One shortcoming of DSMs is that they do not provide a principled way to discriminate different semantic relations. Several approaches have been adopted that rely on annotated data either in the training of the model or later in its evaluation. In this paper, we introduce a dataset for training and evaluating DSMs on semantic relations discrimination between words, in Mandarin, Chinese. The construction of the dataset followed EVALution 1.0, which is an English dataset for the training and evaluating of DSMs. The dataset contains 360 relation pairs, distributed in five different semantic relations, including antonymy, synonymy, hypernymy, meronymy and nearsynonymy. All relation pairs were checked manually to estimate their quality. In the 360 word relation pairs, there are 373 relata. They were all extracted and subsequently manually tagged according to their semantic type. The relatas’ frequency was calculated in a combined corpus of Sinica and Chinese Gigaword. To the best of our knowledge, EVALution-MAN is the first of its kind for Mandarin, Chinese.</abstract>
<identifier type="citekey">hongchao-etal-2016-evalution</identifier>
<location>
<url>https://aclanthology.org/L16-1726</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4583</start>
<end>4587</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EVALution-MAN: A Chinese Dataset for the Training and Evaluation of DSMs
%A Hongchao, Liu
%A Neergaard, Karl
%A Santus, Enrico
%A Huang, Chu-Ren
%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 hongchao-etal-2016-evalution
%X Distributional semantic models (DSMs) are currently being used in the measurement of word relatedness and word similarity. One shortcoming of DSMs is that they do not provide a principled way to discriminate different semantic relations. Several approaches have been adopted that rely on annotated data either in the training of the model or later in its evaluation. In this paper, we introduce a dataset for training and evaluating DSMs on semantic relations discrimination between words, in Mandarin, Chinese. The construction of the dataset followed EVALution 1.0, which is an English dataset for the training and evaluating of DSMs. The dataset contains 360 relation pairs, distributed in five different semantic relations, including antonymy, synonymy, hypernymy, meronymy and nearsynonymy. All relation pairs were checked manually to estimate their quality. In the 360 word relation pairs, there are 373 relata. They were all extracted and subsequently manually tagged according to their semantic type. The relatas’ frequency was calculated in a combined corpus of Sinica and Chinese Gigaword. To the best of our knowledge, EVALution-MAN is the first of its kind for Mandarin, Chinese.
%U https://aclanthology.org/L16-1726
%P 4583-4587
Markdown (Informal)
[EVALution-MAN: A Chinese Dataset for the Training and Evaluation of DSMs](https://aclanthology.org/L16-1726) (Hongchao et al., LREC 2016)
ACL