{"total":30,"rows":[{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152,"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":"2305.13820","title":"An Open Dataset and Model for Language Identification","created":"2023-05-23","cited_by_count":50,"area":null},{"id":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39,"area":null},{"id":"2305.10510","title":"ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages","created":"2023-05-17","cited_by_count":34,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2409.18472","title":"URIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge Base","created":"2024-09-27","cited_by_count":21,"area":null},{"id":"2406.09334","title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models","created":"2024-06-13","cited_by_count":20,"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":"2210.12273","title":"Graphemic Normalization of the Perso-Arabic Script","created":"2022-10-21","cited_by_count":6,"area":null},{"id":"2405.11937","title":"Chasing COMET: Leveraging Minimum Bayes Risk Decoding for Self-Improving Machine Translation","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2511.06531","title":"Ibom NLP: A Step Toward Inclusive Natural Language Processing for Nigeria's Minority Languages","created":"2025-11-09","cited_by_count":6,"area":null},{"id":"2305.10561","title":"Massively Multi-Lingual Event Understanding: Extraction, Visualization, and Search","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2209.02821","title":"Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translation","created":"2022-09-06","cited_by_count":3,"area":null},{"id":"2210.05096","title":"Checks and Strategies for Enabling Code-Switched Machine Translation","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2308.07489","title":"SOTASTREAM: A Streaming Approach to Machine Translation Training","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2407.20438","title":"Generating Gender Alternatives in Machine Translation","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2502.21265","title":"Token-level Ensembling of Models with Different Vocabularies","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2503.20007","title":"Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2506.07506","title":"What Do Indonesians Really Need from Language Technology? A Nationwide Survey","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2211.05015","title":"Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2311.14838","title":"OpusCleaner and OpusTrainer, open source toolkits for training Machine Translation and Large language models","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2405.11942","title":"FAME-MT Dataset: Formality Awareness Made Easy for Machine Translation Purposes","created":"2024-05-20","cited_by_count":1,"area":null},{"id":"2606.12708","title":"AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2510.07203","title":"Sunflower: A New Approach To Expanding Coverage of African Languages in Large Language Models","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2511.03383","title":"Segmentation Beyond Defaults: Asymmetrical Byte Pair Encoding for Optimal Machine Translation Performance","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2604.05624","title":"YoNER: A New Yor\\`ub\\'a Multi-domain Named Entity Recognition Dataset","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2608.05232","title":"Analysis of Numerical Localisation in LLM Translations","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.00515","title":"The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}