# Modeling Target-Side Morphology in Neural Machine Translation: A Comparison of Strategies

arXiv: https://arxiv.org/abs/2203.13550 · HTML: https://mlsanity.com/paper/2203.13550/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 55 references that are in the map.
- First posted on arXiv 25 Mar 2022.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Graph Convolutional Encoders for Syntax-aware Neural Machine Translation](https://mlsanity.com/paper/1704.04675/) (2017)
- [How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs](https://mlsanity.com/paper/1612.04629/) (2016)
- [Tree-to-Sequence Attentional Neural Machine Translation](https://mlsanity.com/paper/1603.06075/) (2016)
- [Linguistically Motivated Vocabulary Reduction for Neural Machine Translation from Turkish to English](https://mlsanity.com/paper/1707.09879/) (2017)
- [Neural versus Phrase-Based Machine Translation Quality: a Case Study](https://mlsanity.com/paper/1608.04631/) (2016)
- [Towards String-to-Tree Neural Machine Translation](https://mlsanity.com/paper/1704.04743/) (2017)
- [Nematus: a Toolkit for Neural Machine Translation](https://mlsanity.com/paper/1703.04357/) (2017)
- [Predicting Target Language CCG Supertags Improves Neural Machine Translation](https://mlsanity.com/paper/1702.01147/) (2017)
- [Sockeye: A Toolkit for Neural Machine Translation](https://mlsanity.com/paper/1712.05690/) (2017)
- [Compositional Representation of Morphologically-Rich Input for Neural Machine Translation](https://mlsanity.com/paper/1805.02036/) (2018)
- [Modeling Target-Side Inflection in Neural Machine Translation](https://mlsanity.com/paper/1707.06012/) (2017)
- [How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?](https://mlsanity.com/paper/2109.01100/) (2021)
- [Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation](https://mlsanity.com/paper/1804.06506/) (2018)
- [Neural Machine Translation by Generating Multiple Linguistic Factors](https://mlsanity.com/paper/1712.01821/) (2017)

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

- [Assessing the Political Fairness of Multilingual LLMs: A Case Study based on a 21-way Multiparallel EuroParl Dataset](https://mlsanity.com/paper/2510.20508/) (2025)

## Abstract (arXiv)

Morphologically rich languages pose difficulties to machine translation. Machine translation engines that rely on statistical learning from parallel training data, such as state-of-the-art neural systems, face challenges especially with rich morphology on the output language side. Key challenges of rich target-side morphology in data-driven machine translation include: (1) A large amount of differently inflected word surface forms entails a larger vocabulary and thus data sparsity. (2) Some inflected forms of infrequent terms typically do not appear in the training corpus, which makes closed-vocabulary systems unable to generate these unobserved variants. (3) Linguistic agreement requires the system to correctly match the grammatical categories between inflected word forms in the output sentence, both in terms of target-side morpho-syntactic wellformedness and semantic adequacy with respect to the input. In this paper, we re-investigate two target-side linguistic processing techniques: a lemma-tag strategy and a linguistically informed word segmentation strategy. Our experiments are conducted on a English-German translation task under three training corpus conditions of different magnitudes. We find that a stronger Transformer baseline leaves less room for improvement than a shallow-RNN encoder-decoder model when translating in-domain. However, we find that linguistic modeling of target-side morphology does benefit the Transformer model when the same system is applied to out-of-domain input text. We also successfully apply our approach to English to Czech translation.