{"total":58,"rows":[{"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":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2112.06598","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","created":"2021-12-13","cited_by_count":89,"area":null},{"id":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"area":null},{"id":"2104.08771","title":"Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation","created":"2021-04-18","cited_by_count":74,"area":null},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57,"area":null},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"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":"2109.02903","title":"IndicBART: A Pre-trained Model for Indic Natural Language Generation","created":"2021-09-07","cited_by_count":39,"area":null},{"id":"2301.09626","title":"Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning","created":"2023-01-23","cited_by_count":26,"area":null},{"id":"2110.08875","title":"Predicting the Performance of Multilingual NLP Models","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2201.03110","title":"Towards the Next 1000 Languages in Multilingual Machine Translation: Exploring the Synergy Between Supervised and Self-Supervised Learning","created":"2022-01-09","cited_by_count":19,"area":null},{"id":"2205.03018","title":"Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users","created":"2022-05-06","cited_by_count":19,"area":null},{"id":"2106.00143","title":"An Exploratory Analysis of Multilingual Word-Level Quality Estimation with Cross-Lingual Transformers","created":"2021-05-31","cited_by_count":18,"area":null},{"id":"2107.04239","title":"A Survey on Low-Resource Neural Machine Translation","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2110.06997","title":"Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits","created":"2021-10-13","cited_by_count":16,"area":null},{"id":"2106.06125","title":"Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation","created":"2021-06-11","cited_by_count":14,"area":null},{"id":"2109.04556","title":"Subword Mapping and Anchoring across Languages","created":"2021-09-09","cited_by_count":12,"area":null},{"id":"2212.12510","title":"MicroBERT: Effective Training of Low-resource Monolingual BERTs through Parameter Reduction and Multitask Learning","created":"2022-12-23","cited_by_count":12,"area":null},{"id":"2104.07483","title":"IndT5: A Text-to-Text Transformer for 10 Indigenous Languages","created":"2021-04-04","cited_by_count":10,"area":null},{"id":"2104.00366","title":"Low-Resource Neural Machine Translation for Southern African Languages","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2109.14934","title":"Prose2Poem: The Blessing of Transformers in Translating Prose to Persian Poetry","created":"2021-09-30","cited_by_count":7,"area":null},{"id":"2306.06804","title":"Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2109.14150","title":"Improving Arabic Diacritization by Learning to Diacritize and Translate","created":"2021-09-29","cited_by_count":6,"area":null},{"id":"2209.13279","title":"Improving Multilingual Neural Machine Translation System for Indic Languages","created":"2022-09-27","cited_by_count":6,"area":null},{"id":"2211.05673","title":"BERT in Plutarch's Shadows","created":"2022-11-10","cited_by_count":6,"area":null},{"id":"2407.05006","title":"Recent Advancements and Challenges of Turkic Central Asian Language Processing","created":"2024-07-06","cited_by_count":6,"area":null},{"id":"2103.04225","title":"Translating the Unseen? Yoruba-English MT in Low-Resource, Morphologically-Unmarked Settings","created":"2021-03-07","cited_by_count":5,"area":null},{"id":"2104.08384","title":"\"Wikily\" Supervised Neural Translation Tailored to Cross-Lingual Tasks","created":"2021-04-16","cited_by_count":5,"area":null},{"id":"2205.08621","title":"Geographical Distance Is The New Hyperparameter: A Case Study Of Finding The Optimal Pre-trained Language For English-isiZulu Machine Translation","created":"2022-05-17","cited_by_count":5,"area":null},{"id":"2103.11088","title":"Token-wise Curriculum Learning for Neural Machine Translation","created":"2021-03-20","cited_by_count":4,"area":null},{"id":"2205.06025","title":"DTW at Qur'an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2205.06993","title":"Improving Neural Machine Translation of Indigenous Languages with Multilingual Transfer Learning","created":"2022-05-14","cited_by_count":4,"area":null},{"id":"2103.13272","title":"Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages","created":"2021-03-24","cited_by_count":3,"area":null},{"id":"2107.12627","title":"Cross-lingual Transferring of Pre-trained Contextualized Language Models","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2109.04443","title":"HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints","created":"2021-09-09","cited_by_count":3,"area":null},{"id":"2205.04067","title":"Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation","created":"2022-05-09","cited_by_count":3,"area":null},{"id":"2205.08605","title":"OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrieval","created":"2022-05-17","cited_by_count":3,"area":null},{"id":"2402.12730","title":"UMBCLU at SemEval-2024 Task 1A and 1C: Semantic Textual Relatedness with and without machine translation","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2405.12612","title":"Tagengo: A Multilingual Chat Dataset","created":"2024-05-21","cited_by_count":3,"area":null},{"id":"2111.10047","title":"Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languages","created":"2021-11-19","cited_by_count":2,"area":null},{"id":"2306.07426","title":"Izindaba-Tindzaba: Machine learning news categorisation for Long and Short Text for isiZulu and Siswati","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2402.13917","title":"Could We Have Had Better Multilingual LLMs If English Was Not the Central Language?","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2510.16743","title":"Zero-Shot Performance Prediction for Probabilistic Scaling Laws","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2103.05951","title":"Self-Learning for Zero Shot Neural Machine Translation","created":"2021-03-10","cited_by_count":1,"area":null},{"id":"2103.15963","title":"Contextual Text Embeddings for Twi","created":"2021-03-29","cited_by_count":1,"area":null},{"id":"2108.03739","title":"Machine Translation of Low-Resource Indo-European Languages","created":"2021-08-08","cited_by_count":1,"area":null},{"id":"2305.03207","title":"Investigating Lexical Sharing in Multilingual Machine Translation for Indian Languages","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2305.05214","title":"CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages","created":"2023-05-09","cited_by_count":1,"area":null},{"id":"2306.00660","title":"Improving Polish to English Neural Machine Translation with Transfer Learning: Effects of Data Volume and Language Similarity","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2602.04764","title":"Beyond Many-Shot Translation: Scaling In-Context Demonstrations For Low-Resource Machine Translation","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2104.00106","title":"Zero-Shot Language Transfer vs Iterative Back Translation for Unsupervised Machine Translation","created":"2021-03-31","cited_by_count":0,"area":null},{"id":"2504.17252","title":"Low-Resource Neural Machine Translation Using Recurrent Neural Networks and Transfer Learning: A Case Study on English-to-Igbo","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2605.04196","title":"The Impact of Vocabulary Overlaps on Knowledge Transfer in Multilingual Machine Translation","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2607.29355","title":"Cross-Lingual Transfer for Machine Translation in Turkic Languages","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.09356","title":"Universal or Language-Family-Specific Script Unification for Cross-Lingual Transfer? A Case Study on Turkic Languages","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}