# Linguistically Motivated Vocabulary Reduction for Neural Machine Translation from Turkish to English

arXiv: https://arxiv.org/abs/1707.09879 · HTML: https://mlsanity.com/paper/1707.09879/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2017.

## Built on by (most cited first, 23 of 23)

- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [The SIGMORPHON 2022 Shared Task on Morpheme Segmentation](https://mlsanity.com/paper/2206.07615/) (2022)
- [A Large-Scale Study of Machine Translation in the Turkic Languages](https://mlsanity.com/paper/2109.04593/) (2021)
- [The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2103.11189/) (2021)
- [Alternative Input Signals Ease Transfer in Multilingual Machine Translation](https://mlsanity.com/paper/2110.07804/) (2021)
- [BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages](https://mlsanity.com/paper/2203.08954/) (2022)
- [Confounding Factors in Relating Model Performance to Morphology](https://mlsanity.com/paper/2511.01380/) (2025)
- [How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation](https://mlsanity.com/paper/2105.13782/) (2021)
- [TurBLiMP: A Turkish Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2506.13487/) (2025)
- [Evaluating Multiway Multilingual NMT in the Turkic Languages](https://mlsanity.com/paper/2109.06262/) (2021)
- [Exploring Segmentation Approaches for Neural Machine Translation of Code-Switched Egyptian Arabic-English Text](https://mlsanity.com/paper/2210.06990/) (2022)
- [Subword-Delimited Downsampling for Better Character-Level Translation](https://mlsanity.com/paper/2212.01304/) (2022)
- [Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction](https://mlsanity.com/paper/2306.06804/) (2023)
- [Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion: An Empirical Study on Chinese and English](https://mlsanity.com/paper/2209.02145/) (2022)
- [A Systematic Analysis of Vocabulary and BPE Settings for Optimal Fine-tuning of NMT: A Case Study of In-domain Translation](https://mlsanity.com/paper/2303.00722/) (2023)
- [Lossless Vocabulary Reduction for Auto-Regressive Language Models](https://mlsanity.com/paper/2510.08102/) (2025)
- [Modelling the Morphology of Verbal Paradigms: A Case Study in the Tokenization of Turkish and Hebrew](https://mlsanity.com/paper/2602.05648/) (2026)
- [Modeling Target-Side Morphology in Neural Machine Translation: A Comparison of Strategies](https://mlsanity.com/paper/2203.13550/) (2022)
- [Benchmarking Azerbaijani Neural Machine Translation](https://mlsanity.com/paper/2207.14473/) (2022)
- [Revisiting Syllables in Language Modelling and their Application on Low-Resource Machine Translation](https://mlsanity.com/paper/2210.02509/) (2022)
- [mALBERT: Is a Compact Multilingual BERT Model Still Worth It?](https://mlsanity.com/paper/2403.18338/) (2024)

## Abstract (arXiv)

The necessity of using a fixed-size word vocabulary in order to control the model complexity in state-of-the-art neural machine translation (NMT) systems is an important bottleneck on performance, especially for morphologically rich languages. Conventional methods that aim to overcome this problem by using sub-word or character-level representations solely rely on statistics and disregard the linguistic properties of words, which leads to interruptions in the word structure and causes semantic and syntactic losses. In this paper, we propose a new vocabulary reduction method for NMT, which can reduce the vocabulary of a given input corpus at any rate while also considering the morphological properties of the language. Our method is based on unsupervised morphology learning and can be, in principle, used for pre-processing any language pair. We also present an alternative word segmentation method based on supervised morphological analysis, which aids us in measuring the accuracy of our model. We evaluate our method in Turkish-to-English NMT task where the input language is morphologically rich and agglutinative. We analyze different representation methods in terms of translation accuracy as well as the semantic and syntactic properties of the generated output. Our method obtains a significant improvement of 2.3 BLEU points over the conventional vocabulary reduction technique, showing that it can provide better accuracy in open vocabulary translation of morphologically rich languages.