{"total":237,"rows":[{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601,"area":null},{"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":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347,"area":null},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284,"area":null},{"id":"2301.07069","title":"Prompting Large Language Model for Machine Translation: A Case Study","created":"2023-01-17","cited_by_count":250,"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":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231,"area":null},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151,"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":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"area":null},{"id":"2303.16104","title":"Hallucinations in Large Multilingual Translation Models","created":"2023-03-28","cited_by_count":129,"area":null},{"id":"2405.15032","title":"Aya 23: Open Weight Releases to Further Multilingual Progress","created":"2024-05-23","cited_by_count":123,"area":null},{"id":"2110.06733","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","created":"2021-10-13","cited_by_count":120,"area":null},{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111,"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":"2105.09501","title":"Contrastive Learning for Many-to-many Multilingual Neural Machine Translation","created":"2021-05-20","cited_by_count":108,"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":"2105.00572","title":"Larger-Scale Transformers for Multilingual Masked Language Modeling","created":"2021-05-02","cited_by_count":87,"area":null},{"id":"2106.12066","title":"It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning","created":"2021-06-22","cited_by_count":69,"area":null},{"id":"2110.10329","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","created":"2021-10-20","cited_by_count":69,"area":null},{"id":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69,"area":null},{"id":"2105.05222","title":"Including Signed Languages in Natural Language Processing","created":"2021-05-11","cited_by_count":68,"area":null},{"id":"2104.14830","title":"Scaling End-to-End Models for Large-Scale Multilingual ASR","created":"2021-04-30","cited_by_count":61,"area":null},{"id":"2209.11379","title":"Do Current Multi-Task Optimization Methods in Deep Learning Even Help?","created":"2022-09-23","cited_by_count":60,"area":null},{"id":"2212.08055","title":"UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units","created":"2022-12-15","cited_by_count":60,"area":null},{"id":"2212.01936","title":"Democratizing Neural Machine Translation with OPUS-MT","created":"2022-12-04","cited_by_count":58,"area":null},{"id":"2108.03265","title":"Facebook AI WMT21 News Translation Task Submission","created":"2021-08-06","cited_by_count":57,"area":null},{"id":"2202.01994","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","created":"2022-02-04","cited_by_count":55,"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":"2310.13448","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":"2105.09259","title":"Learning Language Specific Sub-network for Multilingual Machine Translation","created":"2021-05-19","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":"2111.03945","title":"Towards Building ASR Systems for the Next Billion Users","created":"2021-11-06","cited_by_count":47,"area":null},{"id":"2112.02043","title":"Multilingual training for Software Engineering","created":"2021-12-03","cited_by_count":43,"area":null},{"id":"2204.03508","title":"A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods","created":"2022-04-07","cited_by_count":42,"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":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39,"area":null},{"id":"2103.08647","title":"The Effect of Domain and Diacritics in Yor\\`ub\\'a-English Neural Machine Translation","created":"2021-03-15","cited_by_count":38,"area":null},{"id":"2105.14528","title":"Fast Nearest Neighbor Machine Translation","created":"2021-05-30","cited_by_count":37,"area":null},{"id":"2311.00913","title":"Self-Influence Guided Data Reweighting for Language Model Pre-training","created":"2023-11-02","cited_by_count":37,"area":null},{"id":"2109.04588","title":"BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation","created":"2021-09-09","cited_by_count":35,"area":null},{"id":"2111.02086","title":"Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task","created":"2021-11-03","cited_by_count":34,"area":null},{"id":"2302.01973","title":"Measuring The Impact Of Programming Language Distribution","created":"2023-02-03","cited_by_count":32,"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":"2109.04778","title":"Improving Multilingual Translation by Representation and Gradient Regularization","created":"2021-09-10","cited_by_count":31,"area":null},{"id":"2303.10475","title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges","created":"2023-03-18","cited_by_count":31,"area":null},{"id":"2202.11822","title":"Using natural language prompts for machine translation","created":"2022-02-23","cited_by_count":27,"area":null},{"id":"2302.09650","title":"Scaling Laws for Multilingual Neural Machine Translation","created":"2023-02-19","cited_by_count":27,"area":null},{"id":"2303.02141","title":"Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!","created":"2023-03-03","cited_by_count":27,"area":null},{"id":"2412.04497","title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","created":"2024-11-30","cited_by_count":27,"area":null},{"id":"2202.00528","title":"Examining Scaling and Transfer of Language Model Architectures for Machine Translation","created":"2022-02-01","cited_by_count":26,"area":null},{"id":"2109.04715","title":"AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages","created":"2021-09-10","cited_by_count":24,"area":null},{"id":"2203.08850","title":"Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?","created":"2022-03-16","cited_by_count":24,"area":null},{"id":"2107.06569","title":"Importance-based Neuron Allocation for Multilingual Neural Machine Translation","created":"2021-07-14","cited_by_count":23,"area":null},{"id":"2212.07530","title":"Causes and Cures for Interference in Multilingual Translation","created":"2022-12-14","cited_by_count":23,"area":null},{"id":"2403.03894","title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","created":"2024-03-06","cited_by_count":23,"area":null},{"id":"2410.12883","title":"Scaling Laws for Multilingual Language Models","created":"2024-10-15","cited_by_count":23,"area":null},{"id":"2108.07140","title":"MTG: A Benchmark Suite for Multilingual Text Generation","created":"2021-08-13","cited_by_count":22,"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":"2110.09574","title":"Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters","created":"2021-10-18","cited_by_count":21,"area":null},{"id":"2210.04675","title":"A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing","created":"2022-10-10","cited_by_count":21,"area":null},{"id":"2402.17016","title":"Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings","created":"2024-02-26","cited_by_count":21,"area":null},{"id":"2202.03371","title":"Cedille: A large autoregressive French language model","created":"2022-02-07","cited_by_count":20,"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":"2204.14268","title":"How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?","created":"2022-04-29","cited_by_count":20,"area":null},{"id":"2109.02284","title":"Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training","created":"2021-09-06","cited_by_count":19,"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":"2404.11201","title":"Neuron Specialization: Leveraging intrinsic task modularity for multilingual machine translation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2109.04020","title":"Distributionally Robust Multilingual Machine Translation","created":"2021-09-09","cited_by_count":18,"area":null},{"id":"2305.17682","title":"One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning","created":"2023-05-28","cited_by_count":18,"area":null},{"id":"2311.10174","title":"JWSign: A Highly Multilingual Corpus of Bible Translations for more Diversity in Sign Language Processing","created":"2023-11-16","cited_by_count":18,"area":null},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","cited_by_count":18,"area":null},{"id":"2104.08570","title":"Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems","created":"2021-04-17","cited_by_count":17,"area":null},{"id":"2110.08246","title":"Tricks for Training Sparse Translation Models","created":"2021-10-15","cited_by_count":17,"area":null},{"id":"2311.01070","title":"Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts","created":"2023-11-02","cited_by_count":17,"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":"2110.02600","title":"Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning","created":"2021-10-06","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":"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":"2406.08811","title":"Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models","created":"2024-06-13","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":"2205.10835","title":"Multilingual Machine Translation with Hyper-Adapters","created":"2022-05-22","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":"2109.04705","title":"Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables","created":"2021-09-10","cited_by_count":14,"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":"2101.10368","title":"Meta-Learning for Effective Multi-task and Multilingual Modelling","created":"2021-01-25","cited_by_count":13,"area":null},{"id":"2106.02834","title":"MergeDistill: Merging Pre-trained Language Models using Distillation","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2210.09644","title":"Tencent's Multilingual Machine Translation System for WMT22 Large-Scale African Languages","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2305.02665","title":"Learning Language-Specific Layers for Multilingual Machine Translation","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2408.12780","title":"Quality or Quantity? On Data Scale and Diversity in Adapting Large Language Models for Low-Resource Translation","created":"2024-08-23","cited_by_count":13,"area":null},{"id":"2106.04832","title":"Probing Multilingual Language Models for Discourse","created":"2021-06-09","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":"2206.02079","title":"Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders","created":"2022-06-05","cited_by_count":12,"area":null},{"id":"2502.12301","title":"SMOL: Professionally translated parallel data for 115 under-represented languages","created":"2025-02-17","cited_by_count":12,"area":null},{"id":"2204.04306","title":"MMTAfrica: Multilingual Machine Translation for African Languages","created":"2022-04-08","cited_by_count":11,"area":null}],"next_cursor":"100"}