@inproceedings{stankovic-etal-2016-rule,
title = "Rule-based Automatic Multi-word Term Extraction and Lemmatization",
author = "Stankovi{\'c}, Ranka and
Krstev, Cvetana and
Obradovi{\'c}, Ivan and
Lazi{\'c}, Biljana and
Trtovac, Aleksandra",
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/L16-1081",
pages = "507--514",
abstract = "In this paper we present a rule-based method for multi-word term extraction that relies on extensive lexical resources in the form of electronic dictionaries and finite-state transducers for modelling various syntactic structures of multi-word terms. The same technology is used for lemmatization of extracted multi-word terms, which is unavoidable for highly inflected languages in order to pass extracted data to evaluators and subsequently to terminological e-dictionaries and databases. The approach is illustrated on a corpus of Serbian texts from the mining domain containing more than 600,000 simple word forms. Extracted and lemmatized multi-word terms are filtered in order to reject falsely offered lemmas and then ranked by introducing measures that combine linguistic and statistical information (C-Value, T-Score, LLR, and Keyness). Mean average precision for retrieval of MWU forms ranges from 0.789 to 0.804, while mean average precision of lemma production ranges from 0.956 to 0.960. The evaluation showed that 94{\%} of distinct multi-word forms were evaluated as proper multi-word units, and among them 97{\%} were associated with correct lemmas.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stankovic-etal-2016-rule">
<titleInfo>
<title>Rule-based Automatic Multi-word Term Extraction and Lemmatization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ranka</namePart>
<namePart type="family">Stanković</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cvetana</namePart>
<namePart type="family">Krstev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Obradović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biljana</namePart>
<namePart type="family">Lazić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandra</namePart>
<namePart type="family">Trtovac</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>In this paper we present a rule-based method for multi-word term extraction that relies on extensive lexical resources in the form of electronic dictionaries and finite-state transducers for modelling various syntactic structures of multi-word terms. The same technology is used for lemmatization of extracted multi-word terms, which is unavoidable for highly inflected languages in order to pass extracted data to evaluators and subsequently to terminological e-dictionaries and databases. The approach is illustrated on a corpus of Serbian texts from the mining domain containing more than 600,000 simple word forms. Extracted and lemmatized multi-word terms are filtered in order to reject falsely offered lemmas and then ranked by introducing measures that combine linguistic and statistical information (C-Value, T-Score, LLR, and Keyness). Mean average precision for retrieval of MWU forms ranges from 0.789 to 0.804, while mean average precision of lemma production ranges from 0.956 to 0.960. The evaluation showed that 94% of distinct multi-word forms were evaluated as proper multi-word units, and among them 97% were associated with correct lemmas.</abstract>
<identifier type="citekey">stankovic-etal-2016-rule</identifier>
<location>
<url>https://aclanthology.org/L16-1081</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>507</start>
<end>514</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rule-based Automatic Multi-word Term Extraction and Lemmatization
%A Stanković, Ranka
%A Krstev, Cvetana
%A Obradović, Ivan
%A Lazić, Biljana
%A Trtovac, Aleksandra
%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 stankovic-etal-2016-rule
%X In this paper we present a rule-based method for multi-word term extraction that relies on extensive lexical resources in the form of electronic dictionaries and finite-state transducers for modelling various syntactic structures of multi-word terms. The same technology is used for lemmatization of extracted multi-word terms, which is unavoidable for highly inflected languages in order to pass extracted data to evaluators and subsequently to terminological e-dictionaries and databases. The approach is illustrated on a corpus of Serbian texts from the mining domain containing more than 600,000 simple word forms. Extracted and lemmatized multi-word terms are filtered in order to reject falsely offered lemmas and then ranked by introducing measures that combine linguistic and statistical information (C-Value, T-Score, LLR, and Keyness). Mean average precision for retrieval of MWU forms ranges from 0.789 to 0.804, while mean average precision of lemma production ranges from 0.956 to 0.960. The evaluation showed that 94% of distinct multi-word forms were evaluated as proper multi-word units, and among them 97% were associated with correct lemmas.
%U https://aclanthology.org/L16-1081
%P 507-514
Markdown (Informal)
[Rule-based Automatic Multi-word Term Extraction and Lemmatization](https://aclanthology.org/L16-1081) (Stanković et al., LREC 2016)
ACL
- Ranka Stanković, Cvetana Krstev, Ivan Obradović, Biljana Lazić, and Aleksandra Trtovac. 2016. Rule-based Automatic Multi-word Term Extraction and Lemmatization. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 507–514, Portorož, Slovenia. European Language Resources Association (ELRA).