@inproceedings{L16-1657,
 abstract = {In this paper we describe our effort to create a dataset for the evaluation of cross-language textual similarity detection. We present preexisting corpora and their limits and we explain the various gathered resources to overcome these limits and build our enriched dataset. The proposed dataset is multilingual, includes cross-language alignment for different granularities (from chunk to document), is based on both parallel and comparable corpora and contains human and machine translated texts. Moreover, it includes texts written by multiple types of authors (from average to professionals). With the obtained dataset, we conduct a systematic and rigorous evaluation of several state-of-the-art cross-language textual similarity detection methods. The evaluation results are reviewed and discussed. Finally, dataset and scripts are made publicly available on GitHub: http://github.com/FerreroJeremy/Cross-Language-Dataset.
},
 address = {Portorož, Slovenia},
 author = {Jérémy Ferrero and Frédéric Agnès and Laurent Besacier and Didier Schwab},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {4162--4169},
 publisher = {European Language Resources Association (ELRA)},
 title = {A Multilingual, Multi-style and Multi-granularity Dataset for Cross-language Textual Similarity Detection},
 url = {https://www.aclweb.org/anthology/L16-1657},
 year = {2016}
}