@inproceedings{anwar-sharma-2016-towards,
title = "Towards Building Semantic Role Labeler for {I}ndian Languages",
author = "Anwar, Maaz and
Sharma, Dipti",
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/L16-1727",
pages = "4588--4595",
abstract = "We present a statistical system for identifying the semantic relationships or semantic roles for two major Indian Languages, Hindi and Urdu. Given an input sentence and a predicate/verb, the system first identifies the arguments pertaining to that verb and then classifies it into one of the semantic labels which can either be a DOER, THEME, LOCATIVE, CAUSE, PURPOSE etc. The system is based on 2 statistical classifiers trained on roughly 130,000 words for Urdu and 100,000 words for Hindi that were hand-annotated with semantic roles under the PropBank project for these two languages. Our system achieves an accuracy of 86{\%} in identifying the arguments of a verb for Hindi and 75{\%} for Urdu. At the subsequent task of classifying the constituents into their semantic roles, the Hindi system achieved 58{\%} precision and 42{\%} recall whereas Urdu system performed better and achieved 83{\%} precision and 80{\%} recall. Our study also allowed us to compare the usefulness of different linguistic features and feature combinations in the semantic role labeling task. We also examine the use of statistical syntactic parsing as feature in the role labeling task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="anwar-sharma-2016-towards">
<titleInfo>
<title>Towards Building Semantic Role Labeler for Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maaz</namePart>
<namePart type="family">Anwar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="family">Sharma</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>We present a statistical system for identifying the semantic relationships or semantic roles for two major Indian Languages, Hindi and Urdu. Given an input sentence and a predicate/verb, the system first identifies the arguments pertaining to that verb and then classifies it into one of the semantic labels which can either be a DOER, THEME, LOCATIVE, CAUSE, PURPOSE etc. The system is based on 2 statistical classifiers trained on roughly 130,000 words for Urdu and 100,000 words for Hindi that were hand-annotated with semantic roles under the PropBank project for these two languages. Our system achieves an accuracy of 86% in identifying the arguments of a verb for Hindi and 75% for Urdu. At the subsequent task of classifying the constituents into their semantic roles, the Hindi system achieved 58% precision and 42% recall whereas Urdu system performed better and achieved 83% precision and 80% recall. Our study also allowed us to compare the usefulness of different linguistic features and feature combinations in the semantic role labeling task. We also examine the use of statistical syntactic parsing as feature in the role labeling task.</abstract>
<identifier type="citekey">anwar-sharma-2016-towards</identifier>
<location>
<url>https://aclanthology.org/L16-1727</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4588</start>
<end>4595</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Building Semantic Role Labeler for Indian Languages
%A Anwar, Maaz
%A Sharma, Dipti
%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 anwar-sharma-2016-towards
%X We present a statistical system for identifying the semantic relationships or semantic roles for two major Indian Languages, Hindi and Urdu. Given an input sentence and a predicate/verb, the system first identifies the arguments pertaining to that verb and then classifies it into one of the semantic labels which can either be a DOER, THEME, LOCATIVE, CAUSE, PURPOSE etc. The system is based on 2 statistical classifiers trained on roughly 130,000 words for Urdu and 100,000 words for Hindi that were hand-annotated with semantic roles under the PropBank project for these two languages. Our system achieves an accuracy of 86% in identifying the arguments of a verb for Hindi and 75% for Urdu. At the subsequent task of classifying the constituents into their semantic roles, the Hindi system achieved 58% precision and 42% recall whereas Urdu system performed better and achieved 83% precision and 80% recall. Our study also allowed us to compare the usefulness of different linguistic features and feature combinations in the semantic role labeling task. We also examine the use of statistical syntactic parsing as feature in the role labeling task.
%U https://aclanthology.org/L16-1727
%P 4588-4595
Markdown (Informal)
[Towards Building Semantic Role Labeler for Indian Languages](https://aclanthology.org/L16-1727) (Anwar & Sharma, LREC 2016)
ACL