@inproceedings{aa99367fa09845eba84a79b2663ac726,
title = "SPLIT: Smart preprocessing (quasi) language independent tool",
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.",
keywords = "Corpus linguistics, NLP, Text preprocessing",
author = "Mohamed Al-Badrashiny and Arfath Pasha and Mona Diab and Nizar Habash and Owen Rambow and Wael Salloum and Ramy Eskander",
note = "Funding Information: This paper is based upon work that was partially supported by the Defense Advanced Research Projects Agency (DARPA) under Contract No. HR0011-12-C-0014. Any opinions, findings and conclusions or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of DARPA.; 10th International Conference on Language Resources and Evaluation, LREC 2016 ; Conference date: 23-05-2016 Through 28-05-2016",
year = "2016",
language = "English (US)",
series = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
publisher = "European Language Resources Association (ELRA)",
pages = "4055--4060",
editor = "Nicoletta Calzolari and Khalid Choukri and Helene Mazo and Stelios Piperidis and Asuncion Moreno and Thierry Declerck and Sara Goggi and Marko Grobelnik and Jan Odijk and Joseph Mariani and Bente Maegaard",
booktitle = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
}