# Understanding Translationese in Cross-Lingual Summarization

arXiv: https://arxiv.org/abs/2212.07220 · HTML: https://mlsanity.com/paper/2212.07220/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 72 references that are in the map.
- First posted on arXiv 14 Dec 2022.

## Builds on (most cited first, 26 of 26)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages](https://mlsanity.com/paper/2106.13822/) (2021)
- [WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization](https://mlsanity.com/paper/2010.03093/) (2020)
- [BLEU might be Guilty but References are not Innocent](https://mlsanity.com/paper/2004.06063/) (2020)
- [MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization](https://mlsanity.com/paper/2103.06410/) (2021)
- [Translation Artifacts in Cross-lingual Transfer Learning](https://mlsanity.com/paper/2004.04721/) (2020)
- [Tagged Back-Translation](https://mlsanity.com/paper/1906.06442/) (2019)
- [NCLS: Neural Cross-Lingual Summarization](https://mlsanity.com/paper/1909.00156/) (2019)
- [The Effect of Translationese in Machine Translation Test Sets](https://mlsanity.com/paper/1906.08069/) (2019)
- [MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs](https://mlsanity.com/paper/2104.08692/) (2021)
- [On The Evaluation of Machine Translation Systems Trained With Back-Translation](https://mlsanity.com/paper/1908.05204/) (2019)
- [A Survey on Cross-Lingual Summarization](https://mlsanity.com/paper/2203.12515/) (2022)
- [Translationese as a Language in "Multilingual" NMT](https://mlsanity.com/paper/1911.03823/) (2019)
- [Models and Datasets for Cross-Lingual Summarisation](https://mlsanity.com/paper/2202.09583/) (2022)
- [Post-editese: an Exacerbated Translationese](https://mlsanity.com/paper/1907.00900/) (2019)
- [Cross-Lingual Abstractive Summarization with Limited Parallel Resources](https://mlsanity.com/paper/2105.13648/) (2021)
- [ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization](https://mlsanity.com/paper/2202.05599/) (2022)
- [Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation](https://mlsanity.com/paper/2112.03473/) (2021)
- [Mixed-Lingual Pre-training for Cross-lingual Summarization](https://mlsanity.com/paper/2010.08892/) (2020)
- [A Variational Hierarchical Model for Neural Cross-Lingual Summarization](https://mlsanity.com/paper/2203.03820/) (2022)
- [Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification](https://mlsanity.com/paper/2109.07604/) (2021)
- [On the Language Coverage Bias for Neural Machine Translation](https://mlsanity.com/paper/2106.03297/) (2021)
- [The Cross-lingual Conversation Summarization Challenge](https://mlsanity.com/paper/2205.00379/) (2022)

## Built on by (most cited first, 14 of 14)

- [xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning](https://mlsanity.com/paper/2401.07037/) (2024)
- [Zero-Shot Cross-Lingual Summarization via Large Language Models](https://mlsanity.com/paper/2302.14229/) (2023)
- [Towards Unifying Multi-Lingual and Cross-Lingual Summarization](https://mlsanity.com/paper/2305.09220/) (2023)
- [Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization](https://mlsanity.com/paper/2212.07672/) (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)
- [CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization](https://mlsanity.com/paper/2303.04092/) (2023)
- [StatBot.Swiss: Bilingual Open Data Exploration in Natural Language](https://mlsanity.com/paper/2406.03170/) (2024)
- [D2TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization](https://mlsanity.com/paper/2305.12767/) (2023)
- [Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering](https://mlsanity.com/paper/2406.02331/) (2024)
- [Snowman: A Million-scale Chinese Commonsense Knowledge Graph Distilled from Foundation Model](https://mlsanity.com/paper/2306.10241/) (2023)
- [Fluent Alignment with Disfluent Judges: Post-training for Lower-resource Languages](https://mlsanity.com/paper/2512.08777/) (2025)
- [Benchmarking Concept-Spilling Across Languages in LLMs](https://mlsanity.com/paper/2601.12549/) (2026)
- [Language-Aware Token Boosting: LLM Language Confusion Reduction Without Tuning](https://mlsanity.com/paper/2606.08994/) (2026)

## Abstract (arXiv)

Given a document in a source language, cross-lingual summarization (CLS) aims at generating a concise summary in a different target language. Unlike monolingual summarization (MS), naturally occurring source-language documents paired with target-language summaries are rare. To collect large-scale CLS data, existing datasets typically involve translation in their creation. However, the translated text is distinguished from the text originally written in that language, i.e., translationese. In this paper, we first confirm that different approaches of constructing CLS datasets will lead to different degrees of translationese. Then we systematically investigate how translationese affects CLS model evaluation and performance when it appears in source documents or target summaries. In detail, we find that (1) the translationese in documents or summaries of test sets might lead to the discrepancy between human judgment and automatic evaluation; (2) the translationese in training sets would harm model performance in real-world applications; (3) though machine-translated documents involve translationese, they are very useful for building CLS systems on low-resource languages under specific training strategies. Lastly, we give suggestions for future CLS research including dataset and model developments. We hope that our work could let researchers notice the phenomenon of translationese in CLS and take it into account in the future.