# Merging External Bilingual Pairs into Neural Machine Translation

arXiv: https://arxiv.org/abs/1912.00567 · HTML: https://mlsanity.com/paper/1912.00567/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2019.

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

- [Knowledge Based Template Machine Translation In Low-Resource Setting](https://mlsanity.com/paper/2209.03554/) (2022)

## Abstract (arXiv)

As neural machine translation (NMT) is not easily amenable to explicit correction of errors, incorporating pre-specified translations into NMT is widely regarded as a non-trivial challenge. In this paper, we propose and explore three methods to endow NMT with pre-specified bilingual pairs. Instead, for instance, of modifying the beam search algorithm during decoding or making complex modifications to the attention mechanism --- mainstream approaches to tackling this challenge ---, we experiment with the training data being appropriately pre-processed to add information about pre-specified translations. Extra embeddings are also used to distinguish pre-specified tokens from the other tokens. Extensive experimentation and analysis indicate that over 99% of the pre-specified phrases are successfully translated (given a 85% baseline) and that there is also a substantive improvement in translation quality with the methods explored here.