@InProceedings{pappas-popescubelis:2017:I17-1,
  author    = {Pappas, Nikolaos  and  Popescu-Belis, Andrei},
  title     = {Multilingual Hierarchical Attention Networks for Document Classification},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {1015--1025},
  abstract  = {Hierarchical attention networks have recently achieved remarkable performance
	for document classification in a given language.  However, when multilingual
	document collections are considered, training such models separately for each
	language entails linear parameter growth and lack of cross-language transfer.
	Learning a single multilingual model with fewer parameters is therefore a
	challenging but potentially beneficial objective. To this end, we propose
	multilingual hierarchical attention networks for learning document structures,
	with shared encoders and/or shared attention mechanisms across languages, using
	multi-task learning and an aligned semantic space as input.  We evaluate the
	proposed models on multilingual document classification with disjoint label
	sets, on a large dataset which we provide, with 600k news documents in 8
	languages, and 5k labels.  The multilingual models outperform monolingual ones
	in low-resource as well as full-resource settings, and use fewer parameters,
	thus confirming their computational efficiency and the utility of
	cross-language transfer.},
  url       = {http://www.aclweb.org/anthology/I17-1102}
}