@conference{ESPLGOMIS14.529,
author = "Miquel Espl{\`a}-Gomis and Filip Klubi{\vc}ka and Nikola Ljube{\vs}ić and Sergio Ortiz-Rojas and Papavassiliou, Vassilis and Prokopidis, Prokopis",
abstract = "In this paper we compare two tools for automatically harvesting bitexts from multilingual websites: bitextor and ILSP-FC. We used both tools for crawling 21 multilingual websites from the tourism domain to build a domain-specific English―Croatian parallel corpus. 
Different settings were tried for both tools and 10,662 unique document pairs were obtained. A sample of about 10% of them was manually examined and the success rate was computed on the collection of pairs of documents detected by each setting. We compare the performance of the settings and the amount of different corpora detected by each setting. 
In addition, we describe the resource obtained, both by the settings and through the human evaluation, which has been released as a high-quality parallel corpus.",
address = "Reykjavik, Iceland",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation",
title = "{C}omparing {T}wo {A}cquisition {S}ystems for {A}utomatically {B}uilding an {E}nglish-Croatian {P}arallel {C}orpus from {M}ultilingual {W}ebsites ",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/529_Paper.pdf",
year = "2014",
}