Transactions of the Association for Computational Linguistics · 2018 · 24 citations · 24 references
ComputingComputer ScienceComputational LinguisticsNatural Language ProcessingPhoneticsDeep LearningLanguage ModelingMachine TranslationMulti-task LearningMultilingual Natural Language ProcessingMultilingualismCross-lingual Language ModelingCross-lingual TransferEncoder-decoder ArchitecturesMultilingual Machine TranslationMultitask LearningOrthographic SimilarityTransliteration Systems
We address the task of joint training of transliteration models for multiple language pairs ( multilingual transliteration). This is an instance of multitask learning, where individual tasks (language pairs) benefit from sharing knowledge with related tasks. We focus on transliteration involving related tasks i.e., languages sharing writing systems and phonetic properties ( orthographically similar languages). We propose a modified neural encoder-decoder model that maximizes parameter sharing across language pairs in order to effectively leverage orthographic similarity. We show that multilingual transliteration significantly outperforms bilingual transliteration in different scenarios (average increase of 58% across a variety of languages we experimented with). We also show that multilingual transliteration models can generalize well to languages/language pairs not encountered during training and hence perform well on the zeroshot transliteration task. We show that further improvements can be achieved by using phonetic feature input.
24
Laurens van der Maaten, Geoffrey E. Hinton · Journal of Machine Learning Research · 2008 · 35.7K citations
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Rich Caruana · Machine Learning · 1997 · 6.3K citations · Full text
Denny Vrandečić, Markus Krötzsch · Communications of the ACM · 2014 · 3.3K citations · Full text
Multi-Task Learning for Multiple Language Translation
Daxiang Dong, Hua Wu, Wei He et al. · 2015 · 615 citations · Full text