@inproceedings{al-badrashiny-etal-2016-split,
title = "{SPLIT}: Smart Preprocessing (Quasi) Language Independent Tool",
author = "Al-Badrashiny, Mohamed and
Pasha, Arfath and
Diab, Mona and
Habash, Nizar and
Rambow, Owen and
Salloum, Wael and
Eskander, Ramy",
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/L16-1640",
pages = "4055--4060",
abstract = "Text preprocessing is an important and necessary task for all NLP applications. A simple variation in any preprocessing step may drastically affect the final results. Moreover replicability and comparability, as much as feasible, is one of the goals of our scientific enterprise, thus building systems that can ensure the consistency in our various pipelines would contribute significantly to our goals. The problem has become quite pronounced with the abundance of NLP tools becoming more and more available yet with different levels of specifications. In this paper, we present a dynamic unified preprocessing framework and tool, SPLIT, that is highly configurable based on user requirements which serves as a preprocessing tool for several tools at once. SPLIT aims to standardize the implementations of the most important preprocessing steps by allowing for a unified API that could be exchanged across different researchers to ensure complete transparency in replication. The user is able to select the required preprocessing tasks among a long list of preprocessing steps. The user is also able to specify the order of execution which in turn affects the final preprocessing output.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-badrashiny-etal-2016-split">
<titleInfo>
<title>SPLIT: Smart Preprocessing (Quasi) Language Independent Tool</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Al-Badrashiny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arfath</namePart>
<namePart type="family">Pasha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wael</namePart>
<namePart type="family">Salloum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</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>Text preprocessing is an important and necessary task for all NLP applications. A simple variation in any preprocessing step may drastically affect the final results. Moreover replicability and comparability, as much as feasible, is one of the goals of our scientific enterprise, thus building systems that can ensure the consistency in our various pipelines would contribute significantly to our goals. The problem has become quite pronounced with the abundance of NLP tools becoming more and more available yet with different levels of specifications. In this paper, we present a dynamic unified preprocessing framework and tool, SPLIT, that is highly configurable based on user requirements which serves as a preprocessing tool for several tools at once. SPLIT aims to standardize the implementations of the most important preprocessing steps by allowing for a unified API that could be exchanged across different researchers to ensure complete transparency in replication. The user is able to select the required preprocessing tasks among a long list of preprocessing steps. The user is also able to specify the order of execution which in turn affects the final preprocessing output.</abstract>
<identifier type="citekey">al-badrashiny-etal-2016-split</identifier>
<location>
<url>https://aclanthology.org/L16-1640</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4055</start>
<end>4060</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPLIT: Smart Preprocessing (Quasi) Language Independent Tool
%A Al-Badrashiny, Mohamed
%A Pasha, Arfath
%A Diab, Mona
%A Habash, Nizar
%A Rambow, Owen
%A Salloum, Wael
%A Eskander, Ramy
%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 al-badrashiny-etal-2016-split
%X Text preprocessing is an important and necessary task for all NLP applications. A simple variation in any preprocessing step may drastically affect the final results. Moreover replicability and comparability, as much as feasible, is one of the goals of our scientific enterprise, thus building systems that can ensure the consistency in our various pipelines would contribute significantly to our goals. The problem has become quite pronounced with the abundance of NLP tools becoming more and more available yet with different levels of specifications. In this paper, we present a dynamic unified preprocessing framework and tool, SPLIT, that is highly configurable based on user requirements which serves as a preprocessing tool for several tools at once. SPLIT aims to standardize the implementations of the most important preprocessing steps by allowing for a unified API that could be exchanged across different researchers to ensure complete transparency in replication. The user is able to select the required preprocessing tasks among a long list of preprocessing steps. The user is also able to specify the order of execution which in turn affects the final preprocessing output.
%U https://aclanthology.org/L16-1640
%P 4055-4060
Markdown (Informal)
[SPLIT: Smart Preprocessing (Quasi) Language Independent Tool](https://aclanthology.org/L16-1640) (Al-Badrashiny et al., LREC 2016)
ACL
- Mohamed Al-Badrashiny, Arfath Pasha, Mona Diab, Nizar Habash, Owen Rambow, Wael Salloum, and Ramy Eskander. 2016. SPLIT: Smart Preprocessing (Quasi) Language Independent Tool. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4055–4060, Portorož, Slovenia. European Language Resources Association (ELRA).