# Novel Applications of Factored Neural Machine Translation

arXiv: https://arxiv.org/abs/1910.03912 · HTML: https://mlsanity.com/paper/1910.03912/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [Isochrony-Aware Neural Machine Translation for Automatic Dubbing](https://mlsanity.com/paper/2112.08548/) (2021)
- [Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation](https://mlsanity.com/paper/2105.15087/) (2021)
- [AppTek's Submission to the IWSLT 2022 Isometric Spoken Language Translation Task](https://mlsanity.com/paper/2205.05807/) (2022)
- [Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters](https://mlsanity.com/paper/2305.13204/) (2023)
- [Faithful Target Attribute Prediction in Neural Machine Translation](https://mlsanity.com/paper/2109.12105/) (2021)
- [Explicit Boundary Markers for Subword Vocabularies](https://mlsanity.com/paper/2608.08847/) (2026)

## Abstract (arXiv)

In this work, we explore the usefulness of target factors in neural machine translation (NMT) beyond their original purpose of predicting word lemmas and their inflections, as proposed by Garc`ia-Mart`inez et al., 2016. For this, we introduce three novel applications of the factored output architecture: In the first one, we use a factor to explicitly predict the word case separately from the target word itself. This allows for information to be shared between different casing variants of a word. In a second task, we use a factor to predict when two consecutive subwords have to be joined, eliminating the need for target subword joining markers. The third task is the prediction of special tokens of the operation sequence NMT model (OSNMT) of Stahlberg et al., 2018. Automatic evaluation on English-to-German and English-to-Turkish tasks showed that integration of such auxiliary prediction tasks into NMT is at least as good as the standard NMT approach. For the OSNMT, we observed a significant improvement in BLEU over the baseline OSNMT implementation due to a reduced output sequence length that resulted from the introduction of the target factors.