{"total":126,"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":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343,"area":null},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243,"area":null},{"id":"2309.04662","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","created":"2023-09-09","cited_by_count":181,"area":null},{"id":"2203.00555","title":"DeepNet: Scaling Transformers to 1,000 Layers","created":"2022-03-01","cited_by_count":178,"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":"2202.01374","title":"mSLAM: Massively multilingual joint pre-training for speech and text","created":"2022-02-03","cited_by_count":108,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"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":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"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":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2109.07446","title":"When Does Translation Require Context? A Data-driven, Multilingual Exploration","created":"2021-09-15","cited_by_count":36,"area":null},{"id":"2110.06609","title":"MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators","created":"2021-10-13","cited_by_count":35,"area":null},{"id":"2211.15613","title":"Frustratingly Easy Label Projection for Cross-lingual Transfer","created":"2022-11-28","cited_by_count":33,"area":null},{"id":"2312.02614","title":"Prompt Optimization via Adversarial In-Context Learning","created":"2023-12-05","cited_by_count":33,"area":null},{"id":"2103.06799","title":"Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution","created":"2021-03-11","cited_by_count":31,"area":null},{"id":"2104.00290","title":"Many-to-English Machine Translation Tools, Data, and Pretrained Models","created":"2021-04-01","cited_by_count":31,"area":null},{"id":"2206.09262","title":"Motley: Benchmarking Heterogeneity and Personalization in Federated Learning","created":"2022-06-18","cited_by_count":31,"area":null},{"id":"2106.07930","title":"Language Tags Matter for Zero-Shot Neural Machine Translation","created":"2021-06-15","cited_by_count":29,"area":null},{"id":"2105.07476","title":"Data Augmentation for Sign Language Gloss Translation","created":"2021-05-16","cited_by_count":28,"area":null},{"id":"2202.11822","title":"Using natural language prompts for machine translation","created":"2022-02-23","cited_by_count":27,"area":null},{"id":"2210.12814","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","created":"2022-10-23","cited_by_count":26,"area":null},{"id":"2310.11028","title":"Matrix Compression via Randomized Low Rank and Low Precision Factorization","created":"2023-10-17","cited_by_count":25,"area":null},{"id":"2110.10472","title":"Multilingual Unsupervised Neural Machine Translation with Denoising Adapters","created":"2021-10-20","cited_by_count":22,"area":null},{"id":"2305.14280","title":"Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer","created":"2023-05-23","cited_by_count":22,"area":null},{"id":"2109.04593","title":"A Large-Scale Study of Machine Translation in the Turkic Languages","created":"2021-09-09","cited_by_count":21,"area":null},{"id":"2203.13339","title":"Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation","created":"2022-03-24","cited_by_count":20,"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":"2109.04020","title":"Distributionally Robust Multilingual Machine Translation","created":"2021-09-09","cited_by_count":18,"area":null},{"id":"2203.08307","title":"Improving Word Translation via Two-Stage Contrastive Learning","created":"2022-03-15","cited_by_count":18,"area":null},{"id":"2401.03129","title":"Examining Forgetting in Continual Pre-training of Aligned Large Language Models","created":"2024-01-06","cited_by_count":18,"area":"alignment"},{"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":"2102.07847","title":"Meta Back-translation","created":"2021-02-15","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":"2104.07639","title":"Robust Optimization for Multilingual Translation with Imbalanced Data","created":"2021-04-15","cited_by_count":15,"area":null},{"id":"2305.11550","title":"Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lens","created":"2023-05-19","cited_by_count":15,"area":null},{"id":"2310.19240","title":"M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models","created":"2023-10-30","cited_by_count":15,"area":null},{"id":"2209.15236","title":"Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation","created":"2022-09-30","cited_by_count":14,"area":null},{"id":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2106.03084","title":"Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction","created":"2021-06-06","cited_by_count":12,"area":null},{"id":"2110.10478","title":"Continual Learning in Multilingual NMT via Language-Specific Embeddings","created":"2021-10-20","cited_by_count":12,"area":null},{"id":"2204.09391","title":"You Are What You Write: Preserving Privacy in the Era of Large Language Models","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2210.12929","title":"Finding Memo: Extractive Memorization in Constrained Sequence Generation Tasks","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2311.09071","title":"How Vocabulary Sharing Facilitates Multilingualism in LLaMA?","created":"2023-11-15","cited_by_count":12,"area":null},{"id":"2105.01691","title":"Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution","created":"2021-05-04","cited_by_count":11,"area":null},{"id":"2109.05256","title":"Multilingual Translation via Grafting Pre-trained Language Models","created":"2021-09-11","cited_by_count":10,"area":null},{"id":"2109.06679","title":"Efficient Inference for Multilingual Neural Machine Translation","created":"2021-09-14","cited_by_count":10,"area":null},{"id":"2506.14012","title":"Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text","created":"2025-06-16","cited_by_count":10,"area":null},{"id":"2105.15087","title":"Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation","created":"2021-05-31","cited_by_count":9,"area":null},{"id":"2204.00665","title":"CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation","created":"2022-04-01","cited_by_count":9,"area":null},{"id":"2205.10068","title":"Understanding and Mitigating the Uncertainty in Zero-Shot Translation","created":"2022-05-20","cited_by_count":9,"area":null},{"id":"2209.04161","title":"ApproxTrain: Fast Simulation of Approximate Multipliers for DNN Training and Inference","created":"2022-09-09","cited_by_count":9,"area":null},{"id":"2104.07358","title":"Adaptive Sparse Transformer for Multilingual Translation","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2109.04002","title":"Competence-based Curriculum Learning for Multilingual Machine Translation","created":"2021-09-09","cited_by_count":8,"area":null},{"id":"2110.08130","title":"Breaking Down Multilingual Machine Translation","created":"2021-10-15","cited_by_count":8,"area":null},{"id":"2106.00181","title":"Gender Bias Hidden Behind Chinese Word Embeddings: The Case of Chinese Adjectives","created":"2021-06-01","cited_by_count":7,"area":null},{"id":"2106.05688","title":"AI-enabled Automation for Completeness Checking of Privacy Policies","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2205.11277","title":"When does Parameter-Efficient Transfer Learning Work for Machine Translation?","created":"2022-05-23","cited_by_count":7,"area":null},{"id":"2210.16953","title":"Improving Bilingual Lexicon Induction with Cross-Encoder Reranking","created":"2022-10-30","cited_by_count":7,"area":null},{"id":"2212.09553","title":"Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models","created":"2022-12-19","cited_by_count":7,"area":null},{"id":"2505.14045","title":"From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2104.09810","title":"Addressing the Vulnerability of NMT in Input Perturbations","created":"2021-04-20","cited_by_count":6,"area":null},{"id":"2105.14940","title":"Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?","created":"2021-05-31","cited_by_count":6,"area":null},{"id":"2209.04138","title":"Adapting to Non-Centered Languages for Zero-shot Multilingual Translation","created":"2022-09-09","cited_by_count":6,"area":null},{"id":"2101.09294","title":"Censorship of Online Encyclopedias: Implications for NLP Models","created":"2021-01-22","cited_by_count":5,"area":null},{"id":"2107.02039","title":"Power Law Graph Transformer for Machine Translation and Representation Learning","created":"2021-06-27","cited_by_count":5,"area":null},{"id":"2201.00558","title":"Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Models","created":"2022-01-03","cited_by_count":5,"area":"distill"},{"id":"2602.13139","title":"OpenLID-v3: Improving the Precision of Closely Related Language Identification -- An Experience Report","created":"2026-02-13","cited_by_count":5,"area":null},{"id":"2104.05848","title":"Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation","created":"2021-04-12","cited_by_count":4,"area":null},{"id":"2106.03389","title":"Never guess what I heard... Rumor Detection in Finnish News: a Dataset and a Baseline","created":"2021-06-07","cited_by_count":4,"area":null},{"id":"2106.09325","title":"Central Kurdish machine translation: First large scale parallel corpus and experiments","created":"2021-06-17","cited_by_count":4,"area":null},{"id":"2108.01377","title":"A Dynamic Head Importance Computation Mechanism for Neural Machine Translation","created":"2021-08-03","cited_by_count":4,"area":null},{"id":"2108.07127","title":"Active Learning for Massively Parallel Translation of Constrained Text into Low Resource Languages","created":"2021-08-16","cited_by_count":4,"area":null},{"id":"2507.16083","title":"Efficient Compositional Multi-tasking for On-device Large Language Models","created":"2025-07-21","cited_by_count":4,"area":null},{"id":"2510.13537","title":"K-Merge: Online Continual Merging of Adapters for On-device Large Language Models","created":"2025-10-15","cited_by_count":4,"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":"2302.13574","title":"kNN-BOX: A Unified Framework for Nearest Neighbor Generation","created":"2023-02-27","cited_by_count":3,"area":null},{"id":"2310.14644","title":"Multilingual k-Nearest-Neighbor Machine Translation","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2406.08092","title":"Languages Transferred Within the Encoder: On Representation Transfer in Zero-Shot Multilingual Translation","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2110.07816","title":"Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help?","created":"2021-10-15","cited_by_count":2,"area":"distill"},{"id":"2309.16599","title":"Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2311.17492","title":"Mergen: The First Manchu-Korean Machine Translation Model Trained on Augmented Data","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2312.02820","title":"Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix","created":"2023-12-05","cited_by_count":2,"area":null},{"id":"2404.19505","title":"Context-Aware Machine Translation with Source Coreference Explanation","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2407.12514","title":"On Initializing Transformers with Pre-trained Embeddings","created":"2024-07-17","cited_by_count":2,"area":null},{"id":"2410.19912","title":"Simmering: Sufficient is better than optimal for training neural networks","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2508.17948","title":"Debiasing Multilingual LLMs in Cross-lingual Latent Space","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2510.13848","title":"On-device System of Compositional Multi-tasking in Large Language Models","created":"2025-10-11","cited_by_count":2,"area":null},{"id":"2510.18288","title":"BrailleLLM: Braille Instruction Tuning with Large Language Models for Braille Domain Tasks","created":"2025-10-21","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":"2103.06689","title":"Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddings","created":"2021-03-11","cited_by_count":1,"area":null},{"id":"2201.08070","title":"Linguistically-driven Multi-task Pre-training for Low-resource Neural Machine Translation","created":"2022-01-20","cited_by_count":1,"area":null},{"id":"2203.07643","title":"Can Synthetic Translations Improve Bitext Quality?","created":"2022-03-15","cited_by_count":1,"area":null},{"id":"2209.01530","title":"Informative Language Representation Learning for Massively Multilingual Neural Machine Translation","created":"2022-09-04","cited_by_count":1,"area":null},{"id":"2305.13140","title":"Extrapolating Multilingual Understanding Models as Multilingual Generators","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2307.12835","title":"Joint Dropout: Improving Generalizability in Low-Resource Neural Machine Translation through Phrase Pair Variables","created":"2023-07-24","cited_by_count":1,"area":null},{"id":"2312.01476","title":"Optimizing Context-Enhanced Relational Joins","created":"2023-12-03","cited_by_count":1,"area":null}],"next_cursor":"100"}