ComputingComputer ScienceCorpus-based Translation StudiesNatural Language ProcessingTranslation TheoryMachine TranslationMultilingual Natural Language ProcessingWord EmbeddingsBilingual Text Translation
Word embedding has been found to be highly powerful to translate words from one language to another by a simple linear transform. However, we found some inconsistence among the objective functions of the embedding and the transform learning, as well as the distance measurement. This paper proposes a solution which normalizes the word vectors on a hypersphere and constrains the linear transform as an orthogonal transform. The experimental results confirmed that the proposed solution can offer better performance on a word similarity task and an English-to-Spanish word translation task.
17
Distributed Representations of Words and Phrases and their Compositionality
Tomáš Mikolov, Ilya Sutskever, Kai Chen et al. · arXiv (Cornell University) · 2013 · 18.1K citations · Full text
Natural Language Processing (almost) from Scratch
Ronan Collobert, Jason Weston, Léon Bottou et al. · arXiv (Cornell University) · 2011 · 5.2K citations · Full text
Linguistic Regularities in Continuous Space Word Representations
Tomáš Mikolov, Wen-tau Yih, Geoffrey Zweig · 2013 · 2.9K citations