# Multilingual Distributed Representations without Word Alignment Source: [Multilingual Distributed Representations without Word Alignment]() Collection index: [llms.txt]() Data updated: 2026-01-01T12:01:16.022Z Authors: Karl Moritz Hermann, Phil Blunsom Published: 2013-12-20T23:13:38.000Z ## Abstract Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP. By overcoming data sparsity problems, as well as providing information about semantic relatedness which is not available in discrete representations, distributed representations have proven useful in many NLP tasks. Recent work has shown how compositional semantic representations can successfully be applied to a number of monolingual applications such as sentiment analysis. At the same time, there has been some initial success in work on learning shared word-level representations across languages. We combine these two approaches by proposing a method for learning distributed representations in a multilingual setup. Our model learns to assign similar embeddings to aligned sentences and dissimilar ones to sentence which are not aligned while not requiring word alignments. We show that our representations are semantically informative and apply them to a cross-lingual document classification task where we outperform the previous state of the art. Further, by employing parallel corpora of multiple language pairs we find that our model learns representations that capture semantic relationships across languages for which no parallel data was used. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Cross-lingual Document Classification on Reuters de -\> en](): Cross-lingual Document Classification; Reuters de -\> en; Accuracy: 76.9. - [Cross-lingual Document Classification on Reuters en -\> de (train test)](): Cross-lingual Document Classification; Reuters en -\> de (train test); Accuracy: 0.862. - [Cross-lingual Document Classification on Reuters en -\> de (test)](): Cross-lingual Document Classification; Reuters en -\> de (test); Accuracy: 83.7. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()