# BilBOWA: Fast Bilingual Distributed Representations without Word Alignments

Source: [BilBOWA: Fast Bilingual Distributed Representations without Word Alignments](<https://www.sota2.com/research/paper/68fa62491e209131ce9f89b7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T02:42:56.933Z

Authors: Stephan Gouws, Yoshua Bengio, Greg Corrado

Published: 2014-10-09T13:41:18.000Z

## Abstract

We introduce BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel training data. Instead it trains directly on monolingual data and extracts a bilingual signal from a smaller set of raw-text sentence-aligned data. This is achieved using a novel sampled bag-of-words cross-lingual objective, which is used to regularize two noise-contrastive language models for efficient cross-lingual feature learning. We show that bilingual embeddings learned using the proposed model outperform state-of-the-art methods on a cross-lingual document classification task as well as a lexical translation task on WMT11 data.

## 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.

- [Word Translation on WMT11 English-Spanish (test)](<https://www.sota2.com/research/sota/word-translation-on-wmt11-english-spanish-test.md>): Word Translation; WMT11 English-Spanish (En-\>Sp) (test); P@1: 39.

- [Word Translation on WMT11 English-Spanish (Sp-\>En) (test)](<https://www.sota2.com/research/sota/word-translation-on-wmt11-english-spanish-sp-en-test.md>): Word Translation; WMT11 English-Spanish (Sp-\>En) (test); P@1: 44.

- [Cross-lingual Document Classification on Reuters de -\> en](<https://www.sota2.com/research/sota/cross-lingual-document-classification-on-reuters-de-en.md>): Cross-lingual Document Classification; Reuters de -\> en; Accuracy: 75.

- [Cross-lingual Document Classification on Reuters en -\> de (test)](<https://www.sota2.com/research/sota/cross-lingual-document-classification-on-reuters-en-de-test.md>): Cross-lingual Document Classification; Reuters en -\> de (test); Accuracy: 86.5.

- [Crosslingual Document Classification on RCV1 RCV2 EN -\> DE (test)](<https://www.sota2.com/research/sota/crosslingual-document-classification-on-rcv1-rcv2-en-de-test.md>): Crosslingual Document Classification; RCV1 RCV2 EN -\> DE 1,000 documents per language (test); Accuracy: 86.5.

- [Crosslingual Document Classification on RCV1 RCV2 DE -\> EN (1,000 documents subset, test)](<https://www.sota2.com/research/sota/crosslingual-document-classification-on-rcv1-rcv2-de-en-1-000-documents-subset-test.md>): Crosslingual Document Classification; RCV1 RCV2 DE -\> EN 1,000 documents per language (test); Accuracy: 75.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1410.2455>)

[PDF](<https://arxiv.org/pdf/1410.2455.pdf>)

[Implementation](<https://github.com/gouwsmeister/bilbowa>)