# Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification

arXiv: https://arxiv.org/abs/2109.07604 · HTML: https://mlsanity.com/paper/2109.07604/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 43 references that are in the map.
- First posted on arXiv 15 Sep 2021.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [FastText.zip: Compressing text classification models](https://mlsanity.com/paper/1612.03651/) (2016)
- [Attaining the Unattainable? Reassessing Claims of Human Parity in Neural Machine Translation](https://mlsanity.com/paper/1808.10432/) (2018)
- [The Effect of Translationese in Machine Translation Test Sets](https://mlsanity.com/paper/1906.08069/) (2019)
- [On The Evaluation of Machine Translation Systems Trained With Back-Translation](https://mlsanity.com/paper/1908.05204/) (2019)
- [Translationese in Machine Translation Evaluation](https://mlsanity.com/paper/1906.09833/) (2019)
- [Translationese as a Language in "Multilingual" NMT](https://mlsanity.com/paper/1911.03823/) (2019)
- [Domain, Translationese and Noise in Synthetic Data for Neural Machine Translation](https://mlsanity.com/paper/1911.03362/) (2019)
- [What do Language Representations Really Represent?](https://mlsanity.com/paper/1901.02646/) (2019)
- [Unsupervised Identification of Translationese](https://mlsanity.com/paper/1609.03205/) (2016)
- [Found in Translation: Reconstructing Phylogenetic Language Trees from Translations](https://mlsanity.com/paper/1704.07146/) (2017)
- [The UN Parallel Corpus Annotated for Translation Direction](https://mlsanity.com/paper/1805.07697/) (2018)
- [INFODENS: An Open-source Framework for Learning Text Representations](https://mlsanity.com/paper/1810.07091/) (2018)

## Built on by (most cited first, 13 of 13)

- [High-Dimension Human Value Representation in Large Language Models](https://mlsanity.com/paper/2404.07900/) (2024)
- [Understanding Translationese in Cross-Lingual Summarization](https://mlsanity.com/paper/2212.07220/) (2022)
- [Lost in Literalism: How Supervised Training Shapes Translationese in LLMs](https://mlsanity.com/paper/2503.04369/) (2025)
- [Lost in Translationese? Reducing Translation Effect Using Abstract Meaning Representation](https://mlsanity.com/paper/2304.11501/) (2023)
- [Explaining Translationese: why are Neural Classifiers Better and what do they Learn?](https://mlsanity.com/paper/2210.13391/) (2022)
- [Measuring Spurious Correlation in Classification: 'Clever Hans' in Translationese](https://mlsanity.com/paper/2308.13170/) (2023)
- [Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation](https://mlsanity.com/paper/2408.17308/) (2024)
- [Introducing 3DCNN ResNets for ASD full-body kinematic assessment: a comparison with hand-crafted features](https://mlsanity.com/paper/2311.14533/) (2023)
- [Multi-perspective Alignment for Increasing Naturalness in Neural Machine Translation](https://mlsanity.com/paper/2412.08473/) (2024)
- [Lack of Fluency is Hurting Your Translation Model](https://mlsanity.com/paper/2205.11826/) (2022)
- [Surfing the modeling of PoS taggers in low-resource scenarios](https://mlsanity.com/paper/2402.02449/) (2024)
- [Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese](https://mlsanity.com/paper/2507.12260/) (2025)
- [Translationese as a Rational Response to Translation Task Difficulty](https://mlsanity.com/paper/2603.12050/) (2026)

## Abstract (arXiv)

Traditional hand-crafted linguistically-informed features have often been used for distinguishing between translated and original non-translated texts. By contrast, to date, neural architectures without manual feature engineering have been less explored for this task. In this work, we (i) compare the traditional feature-engineering-based approach to the feature-learning-based one and (ii) analyse the neural architectures in order to investigate how well the hand-crafted features explain the variance in the neural models' predictions. We use pre-trained neural word embeddings, as well as several end-to-end neural architectures in both monolingual and multilingual settings and compare them to feature-engineering-based SVM classifiers. We show that (i) neural architectures outperform other approaches by more than 20 accuracy points, with the BERT-based model performing the best in both the monolingual and multilingual settings; (ii) while many individual hand-crafted translationese features correlate with neural model predictions, feature importance analysis shows that the most important features for neural and classical architectures differ; and (iii) our multilingual experiments provide empirical evidence for translationese universals across languages.