%0 Generic %1 pappas2017multilingual %A Pappas, Nikolaos %A Popescu-Belis, Andrei %D 2017 %K classification multilingualism %T Multilingual Hierarchical Attention Networks for Document Classification %U http://arxiv.org/abs/1707.00896 %X 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 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 strong 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.

@preprint{pappas2017multilingual, 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 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 strong 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.}, added-at = {2017-07-07T16:29:01.000+0200}, author = {Pappas, Nikolaos and Popescu-Belis, Andrei}, biburl = {https://www.bibsonomy.org/bibtex/289121702659711775cd1650f381fcc44/nik0spapp}, description = {Multilingual Hierarchical Attention Networks for Document Classification}, interhash = {a6c20bc48a5f5c33b38a7cdd8fe72935}, intrahash = {89121702659711775cd1650f381fcc44}, keywords = {classification multilingualism}, note = {cite arxiv:1707.00896}, timestamp = {2017-07-07T16:33:42.000+0200}, title = {Multilingual Hierarchical Attention Networks for Document Classification}, url = {http://arxiv.org/abs/1707.00896}, year = 2017 }