# An Autoencoder Approach to Learning Bilingual Word Representations Source: [An Autoencoder Approach to Learning Bilingual Word Representations]() Collection index: [llms.txt]() Data updated: 2025-10-25T19:55:35.464Z Authors: Sarath Chandar A P, Stanislas Lauly, Hugo Larochelle, Mitesh M. Khapra, Balaraman Ravindran, Vikas Raykar, Amrita Saha Published: 2014-02-06T18:53:30.000Z ## Abstract Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this work we explore the use of autoencoder-based methods for cross-language learning of vectorial word representations that are aligned between two languages, while not relying on word-level alignments. We show that by simply learning to reconstruct the bag-of-words representations of aligned sentences, within and between languages, we can in fact learn high-quality representations and do without word alignments. Since training autoencoders on word observations presents certain computational issues, we propose and compare different variations adapted to this setting. We also propose an explicit correlation maximizing regularizer that leads to significant improvement in the performance. We empirically investigate the success of our approach on the problem of cross-language test classification, where a classifier trained on a given language (e.g., English) must learn to generalize to a different language (e.g., German). These experiments demonstrate that our approaches are competitive with the state-of-the-art, achieving up to 10-14 percentage point improvements over the best reported results on this task. ## 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 en -\> de (test)](): Cross-lingual Document Classification; Reuters en -\> de (test); Accuracy: 91.8. - [Crosslingual Document Classification on RCV1 RCV2 EN -\> DE (test)](): Crosslingual Document Classification; RCV1 RCV2 EN -\> DE 1,000 documents per language (test); Accuracy: 91.8. - [Cross-lingual Document Classification on Reuters de -\> en](): Cross-lingual Document Classification; Reuters de -\> en; Accuracy: 72.8. - [Crosslingual Document Classification on RCV1 RCV2 DE -\> EN (1,000 documents subset, test)](): Crosslingual Document Classification; RCV1 RCV2 DE -\> EN 1,000 documents per language (test); Accuracy: 76.7. ## Original sources and implementation [Original paper]() [PDF]()