{"total":68,"rows":[{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560,"area":null},{"id":"2402.17733","title":"Tower: An Open Multilingual Large Language Model for Translation-Related Tasks","created":"2024-02-27","cited_by_count":206,"area":null},{"id":"2104.05596","title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","created":"2021-04-12","cited_by_count":136,"area":null},{"id":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129,"area":null},{"id":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116,"area":null},{"id":"2205.02022","title":"A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation","created":"2022-05-04","cited_by_count":98,"area":null},{"id":"2301.13294","title":"Adaptive Machine Translation with Large Language Models","created":"2023-01-30","cited_by_count":58,"area":null},{"id":"2402.00786","title":"CroissantLLM: A Truly Bilingual French-English Language Model","created":"2024-02-01","cited_by_count":53,"area":null},{"id":"2310.13448","title":"Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning","created":"2023-10-20","cited_by_count":49,"area":null},{"id":"2407.05975","title":"LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages","created":"2024-07-08","cited_by_count":48,"area":null},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47,"area":null},{"id":"2104.06951","title":"Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey","created":"2021-04-14","cited_by_count":46,"area":null},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2405.20089","title":"The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities","created":"2024-05-30","cited_by_count":22,"area":null},{"id":"2408.00397","title":"In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation","created":"2024-08-01","cited_by_count":22,"area":null},{"id":"2312.12740","title":"Fine-tuning Large Language Models for Adaptive Machine Translation","created":"2023-12-20","cited_by_count":21,"area":null},{"id":"2105.15071","title":"Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data","created":"2021-05-31","cited_by_count":17,"area":null},{"id":"2210.11621","title":"SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages","created":"2022-10-20","cited_by_count":16,"area":null},{"id":"2409.17892","title":"EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2106.11891","title":"On the Evaluation of Machine Translation for Terminology Consistency","created":"2021-06-22","cited_by_count":15,"area":null},{"id":"2503.04554","title":"Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation","created":"2025-03-06","cited_by_count":14,"area":null},{"id":"2208.05909","title":"Domain-Specific Text Generation for Machine Translation","created":"2022-08-11","cited_by_count":12,"area":null},{"id":"2501.06374","title":"AFRIDOC-MT: Document-level MT Corpus for African Languages","created":"2025-01-10","cited_by_count":11,"area":null},{"id":"2504.12140","title":"Multilingual Contextualization of Large Language Models for Document-Level Machine Translation","created":"2025-04-16","cited_by_count":11,"area":null},{"id":"2108.06598","title":"Findings of the LoResMT 2021 Shared Task on COVID and Sign Language for Low-resource Languages","created":"2021-08-14","cited_by_count":10,"area":null},{"id":"2305.17267","title":"CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2602.05879","title":"EuroLLM-22B: Technical Report","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2107.08357","title":"As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation","created":"2021-07-18","cited_by_count":8,"area":null},{"id":"2212.07571","title":"Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation","created":"2022-12-15","cited_by_count":8,"area":"moe"},{"id":"2502.13780","title":"Translation in the Hands of Many:Centering Lay Users in Machine Translation Interactions","created":"2025-02-19","cited_by_count":8,"area":null},{"id":"2503.06594","title":"Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation","created":"2025-03-09","cited_by_count":8,"area":"inference"},{"id":"2404.02392","title":"Low-resource neural machine translation with morphological modeling","created":"2024-04-03","cited_by_count":7,"area":null},{"id":"2410.09948","title":"State of NLP in Kenya: A Survey","created":"2024-10-13","cited_by_count":7,"area":null},{"id":"2504.11582","title":"AskQE: Question Answering as Automatic Evaluation for Machine Translation","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2210.12273","title":"Graphemic Normalization of the Perso-Arabic Script","created":"2022-10-21","cited_by_count":6,"area":null},{"id":"2103.10734","title":"Congolese Swahili Machine Translation for Humanitarian Response","created":"2021-03-19","cited_by_count":5,"area":null},{"id":"2110.07444","title":"Designing Language Technologies for Social Good: The Road not Taken","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2505.24683","title":"Should I Share this Translation? Evaluating Quality Feedback for User Reliance on Machine Translation","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2211.01292","title":"Learning an Artificial Language for Knowledge-Sharing in Multilingual Translation","created":"2022-11-02","cited_by_count":4,"area":null},{"id":"2409.07131","title":"Reranking Laws for Language Generation: A Communication-Theoretic Perspective","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2409.12737","title":"MEXMA: Token-level objectives improve sentence representations","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2503.04797","title":"Parallel Corpora for Machine Translation in Low-resource Indic Languages: A Comprehensive Review","created":"2025-03-02","cited_by_count":4,"area":null},{"id":"2210.15861","title":"Domain Adaptation of Machine Translation with Crowdworkers","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2412.05862","title":"Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis","created":"2024-12-08","cited_by_count":3,"area":null},{"id":"2505.02463","title":"Data Augmentation With Back translation for Low Resource languages: A case of English and Luganda","created":"2025-05-05","cited_by_count":3,"area":null},{"id":"2508.03523","title":"FilBench: Can LLMs Understand and Generate Filipino?","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2305.14124","title":"When Does Monolingual Data Help Multilingual Translation: The Role of Domain and Model Scale","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2407.07413","title":"KpopMT: Translation Dataset with Terminology for Kpop Fandom","created":"2024-07-10","cited_by_count":2,"area":null},{"id":"2602.09373","title":"AfriNLLB: Efficient Translation Models for African Languages","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2109.04292","title":"Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection","created":"2021-09-09","cited_by_count":1,"area":null},{"id":"2204.02790","title":"Global Readiness of Language Technology for Healthcare: What would it Take to Combat the Next Pandemic?","created":"2022-04-06","cited_by_count":1,"area":null},{"id":"2502.03053","title":"DOLFIN -- Document-Level Financial test set for Machine Translation","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2502.16961","title":"UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2505.14244","title":"TransBench: Benchmarking Machine Translation for Industrial-Scale Applications","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2508.08680","title":"TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2508.16048","title":"OpenWHO: A Document-Level Parallel Corpus for Health Translation in Low-Resource Languages","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2602.13452","title":"LLM-Powered Automatic Translation and Urgency in Crisis Scenarios","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2604.26597","title":"Translating Under Pressure: Domain-Aware LLMs for Crisis Communication","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2111.03813","title":"Analyzing Architectures for Neural Machine Translation Using Low Computational Resources","created":"2021-11-06","cited_by_count":0,"area":null},{"id":"2503.07195","title":"Contextual Cues in Machine Translation: Investigating the Potential of Multi-Source Input Strategies in LLMs and NMT Systems","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2504.04155","title":"GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models","created":"2025-04-05","cited_by_count":0,"area":null},{"id":"2604.00613","title":"English to Central Kurdish Speech Translation: Corpus Creation, Evaluation, and Orthographic Standardization","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.22828","title":"A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Development","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.28315","title":"HardMTBench: Stress-Testing Chinese-English Translation on Knowledge-Intensive Domains","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.22300","title":"Biomedical Machine Translation for Low-Resource Arabic-Script Languages via Cross-Lingual Transfer and LoRA Adapter Merging","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2610.16646","title":"SIREN: Situation-aware Index for Response and Emergency ActioNability in Crisis Translation","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}