# Bilingual is At Least Monolingual (BALM): A Novel Translation Algorithm that Encodes Monolingual Priors

arXiv: https://arxiv.org/abs/1909.01146 · HTML: https://mlsanity.com/paper/1909.01146/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2019.

## Built on by (most cited first, 1 of 1)

- [BERT2Code: Can Pretrained Language Models be Leveraged for Code Search?](https://mlsanity.com/paper/2104.08017/) (2021)

## Abstract (arXiv)

State-of-the-art machine translation (MT) models do not use knowledge of any single language's structure; this is the equivalent of asking someone to translate from English to German while knowing neither language. BALM is a framework incorporates monolingual priors into an MT pipeline; by casting input and output languages into embedded space using BERT, we can solve machine translation with much simpler models. We find that English-to-German translation on the Multi30k dataset can be solved with a simple feedforward network under the BALM framework with near-SOTA BLEU scores.