@inproceedings{858db936ab0e4f9eaeafda420aa3b1ba,
title = "Two architectures for parallel processing of huge amounts of text",
abstract = "This paper presents two alternative NLP architectures to analyze massive amounts of documents, using parallel processing. The two architectures focus on different processing scenarios, namely batch-processing and streaming processing. The batch-processing scenario aims at optimizing the overall throughput of the system, i.e., minimizing the overall time spent on processing all documents. The streaming architecture aims to minimize the time to process real-time incoming documents and is therefore especially suitable for live feeds. The paper presents experiments with both architectures, and reports the overall gain when they are used for batch as well as for streaming processing. All the software described in the paper is publicly available under free licenses.",
keywords = "Big data, Parallel processing, System architecture",
author = "Mathijs Kattenberg and Zuhaitz Beloki and Aitor Soroa and Xabier Artola and Antske Fokkens and Paul Huygen and Kees Verstoep",
year = "2016",
language = "English",
series = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
publisher = "European Language Resources Association (ELRA)",
pages = "4513--4519",
editor = "Nicoletta Calzolari and Khalid Choukri and Helene Mazo and Asuncion Moreno and Thierry Declerck and Sara Goggi and Marko Grobelnik and Jan Odijk and Stelios Piperidis and Bente Maegaard and Joseph Mariani",
booktitle = "Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016",
note = "10th International Conference on Language Resources and Evaluation, LREC 2016 ; Conference date: 23-05-2016 Through 28-05-2016",
}