@inproceedings{simi-attardi-2016-adapting,
title = "Adapting the {TANL} tool suite to {U}niversal {D}ependencies",
author = "Simi, Maria and
Attardi, Giuseppe",
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/L16-1264",
pages = "1672--1678",
abstract = "TANL is a suite of tools for text analytics based on the software architecture paradigm of data driven pipelines. The strategies for upgrading TANL to the use of Universal Dependencies range from a minimalistic approach consisting of introducing pre/post-processing steps into the native pipeline to revising the whole pipeline. We explore the issue in the context of the Italian Treebank, considering both the efforts involved, how to avoid losing linguistically relevant information and the loss of accuracy in the process. In particular we compare different strategies for parsing and discuss the implications of simplifying the pipeline when detailed part-of-speech and morphological annotations are not available, as it is the case for less resourceful languages. The experiments are relative to the Italian linguistic pipeline, but the use of different parsers in our evaluations and the avoidance of language specific tagging make the results general enough to be useful in helping the transition to UD for other languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simi-attardi-2016-adapting">
<titleInfo>
<title>Adapting the TANL tool suite to Universal Dependencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Simi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Attardi</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>TANL is a suite of tools for text analytics based on the software architecture paradigm of data driven pipelines. The strategies for upgrading TANL to the use of Universal Dependencies range from a minimalistic approach consisting of introducing pre/post-processing steps into the native pipeline to revising the whole pipeline. We explore the issue in the context of the Italian Treebank, considering both the efforts involved, how to avoid losing linguistically relevant information and the loss of accuracy in the process. In particular we compare different strategies for parsing and discuss the implications of simplifying the pipeline when detailed part-of-speech and morphological annotations are not available, as it is the case for less resourceful languages. The experiments are relative to the Italian linguistic pipeline, but the use of different parsers in our evaluations and the avoidance of language specific tagging make the results general enough to be useful in helping the transition to UD for other languages.</abstract>
<identifier type="citekey">simi-attardi-2016-adapting</identifier>
<location>
<url>https://aclanthology.org/L16-1264</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1672</start>
<end>1678</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adapting the TANL tool suite to Universal Dependencies
%A Simi, Maria
%A Attardi, Giuseppe
%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 simi-attardi-2016-adapting
%X TANL is a suite of tools for text analytics based on the software architecture paradigm of data driven pipelines. The strategies for upgrading TANL to the use of Universal Dependencies range from a minimalistic approach consisting of introducing pre/post-processing steps into the native pipeline to revising the whole pipeline. We explore the issue in the context of the Italian Treebank, considering both the efforts involved, how to avoid losing linguistically relevant information and the loss of accuracy in the process. In particular we compare different strategies for parsing and discuss the implications of simplifying the pipeline when detailed part-of-speech and morphological annotations are not available, as it is the case for less resourceful languages. The experiments are relative to the Italian linguistic pipeline, but the use of different parsers in our evaluations and the avoidance of language specific tagging make the results general enough to be useful in helping the transition to UD for other languages.
%U https://aclanthology.org/L16-1264
%P 1672-1678
Markdown (Informal)
[Adapting the TANL tool suite to Universal Dependencies](https://aclanthology.org/L16-1264) (Simi & Attardi, LREC 2016)
ACL
- Maria Simi and Giuseppe Attardi. 2016. Adapting the TANL tool suite to Universal Dependencies. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1672–1678, Portorož, Slovenia. European Language Resources Association (ELRA).