mlsanityData to 7 Oct 2026

Revisiting Machine Translation for Cross-lingual Classification

arXiv 2305.14240 ↗First posted 23 May 2023cs.CL cs.AI cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

Machine Translation (MT) has been widely used for cross-lingual classification, either by translating the test set into English and running inference with a monolingual model (translate-test), or translating the training set into the target languages and finetuning a multilingual model (translate-train). However, most research in the area focuses on the multilingual models rather than the MT component. We show that, by using a stronger MT system and mitigating the mismatch between training on original text and running inference on machine translated text, translate-test can do substantially better than previously assumed. The optimal approach, however, is highly task dependent, as we identify various sources of cross-lingual transfer gap that affect different tasks and approaches differently. Our work calls into question the dominance of multilingual models for cross-lingual classification, and prompts to pay more attention to MT-based baselines.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 33 of its 45 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

33 of 45 references.

References · 33

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  6. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  7. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  8. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  9. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  10. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  11. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  12. 2018XNLI: Evaluating Cross-lingual Sentence Representationscited by 913
21 more
  1. 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 738
  2. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 518
  3. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 395
  4. 2018SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inferencecited by 333
  5. 2020XCOPA: A Multilingual Dataset for Causal Commonsense Reasoningcited by 330
  6. 2019PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identificationcited by 262
  7. 2021XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluationcited by 167
  8. 2020The Multilingual Amazon Reviews Corpuscited by 142
  9. 2020Translation Artifacts in Cross-lingual Transfer Learningcited by 95
  10. 2021XLM-E: Cross-lingual Language Model Pre-training via ELECTRAcited by 72
  11. 2020EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answeringcited by 60
  12. 2020Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpuscited by 49
  13. 2021A Primer on Pretrained Multilingual Language Modelscited by 49
  14. 2021Consistency Regularization for Cross-Lingual Fine-Tuningcited by 41
  15. 2019Entity Projection via Machine Translation for Cross-Lingual NERcited by 32
  16. 2020FILTER: An Enhanced Fusion Method for Cross-lingual Language Understandingcited by 29
  17. 2022Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settingscited by 21
  18. 2021Should we Stop Training More Monolingual Models, and Simply Use Machine Translation Instead?cited by 16
  19. 2021Modelling Latent Translations for Cross-Lingual Transfercited by 16
  20. 2022T-Projection: High Quality Annotation Projection for Sequence Labeling Taskscited by 14
  21. 2022Synergy with Translation Artifacts for Training and Inference in Multilingual Taskscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 15; 2025: 10; 2026: 7.

40 papers.

Sort:

By area:

  1. 2023Do Multilingual Language Models Think Better in English?cited by 87
  2. 2024Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontierscited by 49
  3. 2024Question Translation Training for Better Multilingual Reasoningcited by 41
  4. 2024Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Modelscited by 31
  5. 2024Fine-tuning Large Language Models with Sequential Instructionscited by 20
  6. 2024Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challengescited by 18
  7. 2023Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptationcited by 11
  8. 2024Translation Errors Significantly Impact Low-Resource Languages in Cross-Lingual Learningcited by 9
  9. 2024Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languagescited by 9
  10. 2024Constrained Decoding for Cross-lingual Label Projectioncited by 8
  11. 2024Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scriptscited by 8
  12. 2023To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languagescited by 7
28 more
  1. 2026Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoningcited by 6
  2. 2024Chain-of-Translation Prompting (CoTR): A Novel Prompting Technique for Low Resource Languagescited by 5
  3. 2024Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switchingcited by 5
  4. 2025How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucinationcited by 5
  5. 2026Multilingual Safety Alignment Via Sparse Weight Editingcited by 5
  6. 2025Translate, then Detect: Leveraging Machine Translation for Cross-Lingual Toxicity Classificationcited by 4
  7. 2024Self-Translate-Train: Enhancing Cross-Lingual Transfer of Large Language Models via Inherent Capabilitycited by 3
  8. 2025Language Fusion for Parameter-Efficient Cross-lingual Transfercited by 3
  9. 2023Interpreting Indirect Answers to Yes-No Questions in Multiple Languagescited by 2
  10. 2023Zero-Shot Cross-Lingual Sentiment Classification under Distribution Shift: an Exploratory Studycited by 2
  11. 2024Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answeringcited by 2
  12. 2025The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Taskscited by 2
  13. 2025When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answeringcited by 2
  14. 2026Language on Demand, Knowledge at Core: Composing LLMs with Encoder-Decoder Translation Models for Extensible Multilingualitycited by 2
  15. 2023Optimal strategies to perform multilingual analysis of social content for a novel dataset in the tourism domaincited by 1
  16. 2025Multilingual Self-Taught Faithfulness Evaluatorscited by 1
  17. 2025Learning the Topic, Not the Language: How LLMs Classify Online Immigration Discourse Across Languagescited by 1
  18. 2025Everyday Physics in Korean Contexts: A Culturally Grounded Physical Reasoning Benchmarkcited by 1
  19. 2026A Cost-Efficient Routing Pipeline for Multilingual Short-Text Classification Using Small Language Modelscited by 1
  20. 2023Rosetta Stone at KSAA-RD Shared Task: A Hop From Language Modeling To Word--Definition Alignmentcited by 0
  21. 2023CUNI Submission to MRL 2023 Shared Task on Multi-lingual Multi-task Information Retrievalcited by 0
  22. 2024Boosting Zero-Shot Crosslingual Performance using LLM-Based Augmentations with Effective Data Selectioncited by 0
  23. 2024"Is Hate Lost in Translation?": Evaluation of Multilingual LGBTQIA+ Hate Speech Detectioncited by 0
  24. 2025Toward Robust Multilingual Adaptation of LLMs for Low-Resource Languagescited by 0
  25. 2025TransAlign: Machine Translation Encoders are Strong Word Aligners, Toocited by 0
  26. 2026BYOL: Bring Your Own Language Into LLMscited by 0
  27. 2026From Synthetic to Native: Benchmarking Multilingual Intent Classification in Logistics Customer Servicecited by 0
  28. 2026Discovering Translation-Worthy Languages with E-Valuescited by 0