# A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings

arXiv: https://arxiv.org/abs/2112.13960 · HTML: https://mlsanity.com/paper/2112.13960/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 28 Dec 2021.

## Builds on (most cited first, 8 of 8)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Guided Alignment Training for Topic-Aware Neural Machine Translation](https://mlsanity.com/paper/1607.01628/) (2016)
- [LSTM Neural Reordering Feature for Statistical Machine Translation](https://mlsanity.com/paper/1512.00177/) (2015)
- [Neural Machine Translation on Scarce-Resource Condition: A case-study on Persian-English](https://mlsanity.com/paper/1701.01854/) (2017)
- [Monolingually Derived Phrase Scores for Phrase Based SMT Using Neural Networks Vector Representations](https://mlsanity.com/paper/1506.00406/) (2015)

## Abstract (arXiv)

Neural Machine Translation (NMT) models are strong enough to convey semantic and syntactic information from the source language to the target language. However, these models are suffering from the need for a large amount of data to learn the parameters. As a result, for languages with scarce data, these models are at risk of underperforming. We propose to augment attention based neural network with reordering information to alleviate the lack of data. This augmentation improves the translation quality for both English to Persian and Persian to English by up to 6% BLEU absolute over the baseline models.