@inproceedings{d833ed75f30f4bbfbfe3b8d892486742,
title = "Multilingual clustering of streaming news",
abstract = "Clustering news across languages enables efficient media monitoring by aggregating articles from multilingual sources into coherent stories. Doing so in an online setting allows scalable processing of massive news streams. To this end, we describe a novel method for clustering an incoming stream of multilingual documents into monolingual and crosslingual story clusters. Unlike typical clustering approaches that consider a small and known number of labels, we tackle the problem of discovering an ever growing number of cluster labels in an online fashion, using real news datasets in multiple languages. Our method is simple to implement, computationally efficient and produces state-of-the-art results on datasets in German, English and Spanish.",
author = "Sebasti{\~a}o Miranda and Artūrs Znotiņ{\v s} and Cohen, \{Shay B.\} and Guntis Bārzdiņ{\v s}",
note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics",
year = "2018",
language = "English",
isbn = "9781948087841",
series = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",
publisher = "Association for Computational Linguistics",
pages = "4535--4544",
editor = "Ellen Riloff and David Chiang and Julia Hockenmaier and Jun'ichi Tsujii",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",
address = "United States",
}