{"total":117,"rows":[{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631,"area":"moe"},{"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":"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":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2309.16575","title":"A Benchmark for Learning to Translate a New Language from One Grammar Book","created":"2023-09-28","cited_by_count":75,"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":"2303.01911","title":"Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM","created":"2023-03-03","cited_by_count":59,"area":null},{"id":"2108.03265","title":"Facebook AI WMT21 News Translation Task Submission","created":"2021-08-06","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":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"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":"2309.07098","title":"Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding","created":"2023-09-13","cited_by_count":42,"area":null},{"id":"2104.08154","title":"Counter-Interference Adapter for Multilingual Machine Translation","created":"2021-04-16","cited_by_count":40,"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":"2106.07930","title":"Language Tags Matter for Zero-Shot Neural Machine Translation","created":"2021-06-15","cited_by_count":29,"area":null},{"id":"2202.11822","title":"Using natural language prompts for machine translation","created":"2022-02-23","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":"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":"2110.10472","title":"Multilingual Unsupervised Neural Machine Translation with Denoising Adapters","created":"2021-10-20","cited_by_count":22,"area":null},{"id":"2105.04846","title":"Can You Traducir This? Machine Translation for Code-Switched Input","created":"2021-05-11","cited_by_count":21,"area":null},{"id":"2212.10551","title":"Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation","created":"2022-12-20","cited_by_count":21,"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":"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":"2109.04020","title":"Distributionally Robust Multilingual Machine Translation","created":"2021-09-09","cited_by_count":18,"area":null},{"id":"2110.08246","title":"Tricks for Training Sparse Translation Models","created":"2021-10-15","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":"2110.06997","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":"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":"2105.03010","title":"Efficient Weight factorization for Multilingual Speech Recognition","created":"2021-05-07","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":"2203.09210","title":"Universal Conditional Masked Language Pre-training for Neural Machine Translation","created":"2022-03-17","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":"2310.12462","title":"Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights","created":"2023-10-19","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},{"id":"2109.05256","title":"Multilingual Translation via Grafting Pre-trained Language Models","created":"2021-09-11","cited_by_count":10,"area":null},{"id":"2305.07310","title":"Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization","created":"2023-05-12","cited_by_count":10,"area":null},{"id":"2305.15718","title":"Towards Higher Pareto Frontier in Multilingual Machine Translation","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2110.08130","title":"Breaking Down Multilingual Machine Translation","created":"2021-10-15","cited_by_count":8,"area":null},{"id":"2303.15265","title":"Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation","created":"2023-03-27","cited_by_count":8,"area":null},{"id":"2305.12449","title":"Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter","created":"2023-05-21","cited_by_count":8,"area":null},{"id":"2406.11432","title":"AnyTrans: Translate AnyText in the Image with Large Scale Models","created":"2024-06-17","cited_by_count":8,"area":"diffusion"},{"id":"2104.00366","title":"Low-Resource Neural Machine Translation for Southern African Languages","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2109.10341","title":"Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents","created":"2021-09-21","cited_by_count":7,"area":null},{"id":"2203.07627","title":"Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation","created":"2022-03-15","cited_by_count":7,"area":null},{"id":"2312.06134","title":"Order Matters in the Presence of Dataset Imbalance for Multilingual Learning","created":"2023-12-11","cited_by_count":7,"area":null},{"id":"2205.10019","title":"Translating Hanja Historical Documents to Contemporary Korean and English","created":"2022-05-20","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":"2101.11349","title":"Triangular Bidword Generation for Sponsored Search Auction","created":"2021-01-27","cited_by_count":5,"area":null},{"id":"2112.11482","title":"English2Gbe: A multilingual machine translation model for {Fon/Ewe}Gbe","created":"2021-12-13","cited_by_count":5,"area":null},{"id":"2112.13619","title":"Parameter Differentiation based Multilingual Neural Machine Translation","created":"2021-12-27","cited_by_count":5,"area":null},{"id":"2212.02800","title":"Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation","created":"2022-12-06","cited_by_count":5,"area":"distill"},{"id":"2304.09388","title":"An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models","created":"2023-04-19","cited_by_count":5,"area":"distill"},{"id":"2311.07439","title":"Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models","created":"2023-11-13","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":"2106.05141","title":"AUGVIC: Exploiting BiText Vicinity for Low-Resource NMT","created":"2021-06-09","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":"2109.05179","title":"Asking Questions Like Educational Experts: Automatically Generating Question-Answer Pairs on Real-World Examination Data","created":"2021-09-11","cited_by_count":4,"area":null},{"id":"2207.04906","title":"HLT-MT: High-resource Language-specific Training for Multilingual Neural Machine Translation","created":"2022-07-11","cited_by_count":4,"area":null},{"id":"2210.15851","title":"Improving Zero-Shot Multilingual Translation with Universal Representations and Cross-Mappings","created":"2022-10-28","cited_by_count":4,"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":"2408.07445","title":"Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2102.06578","title":"Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders","created":"2021-02-12","cited_by_count":3,"area":null},{"id":"2106.03484","title":"BERTGEN: Multi-task Generation through BERT","created":"2021-06-07","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":"2210.06068","title":"Investigating Massive Multilingual Pre-Trained Machine Translation Models for Clinical Domain via Transfer Learning","created":"2022-10-12","cited_by_count":3,"area":null},{"id":"2301.04434","title":"Multilingual Entity and Relation Extraction from Unified to Language-specific Training","created":"2023-01-11","cited_by_count":3,"area":null},{"id":"2403.20157","title":"A Systematic Analysis of Subwords and Cross-Lingual Transfer in Multilingual Translation","created":"2024-03-29","cited_by_count":3,"area":null},{"id":"2411.06506","title":"CULL-MT: Compression Using Language and Layer pruning for Machine Translation","created":"2024-11-10","cited_by_count":3,"area":null},{"id":"2102.08357","title":"Revisiting Language Encoding in Learning Multilingual Representations","created":"2021-02-16","cited_by_count":2,"area":null},{"id":"2103.03589","title":"Hierarchical Transformer for Multilingual Machine Translation","created":"2021-03-05","cited_by_count":2,"area":null},{"id":"2109.10197","title":"One Source, Two Targets: Challenges and Rewards of Dual Decoding","created":"2021-09-21","cited_by_count":2,"area":null},{"id":"2109.14368","title":"EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT","created":"2021-09-29","cited_by_count":2,"area":null},{"id":"2110.07304","title":"An Empirical Investigation of Multi-bridge Multilingual NMT models","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2201.02009","title":"PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation","created":"2022-01-06","cited_by_count":2,"area":null},{"id":"2205.01620","title":"Unifying the Convergences in Multilingual Neural Machine Translation","created":"2022-05-03","cited_by_count":2,"area":null},{"id":"2210.14979","title":"Robust Domain Adaptation for Pre-trained Multilingual Neural Machine Translation Models","created":"2022-10-26","cited_by_count":2,"area":null},{"id":"2302.03528","title":"Efficiently Upgrading Multilingual Machine Translation Models to Support More Languages","created":"2023-02-07","cited_by_count":2,"area":null},{"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":"2310.15114","title":"How To Build Competitive Multi-gender Speech Translation Models For Controlling Speaker Gender Translation","created":"2023-10-23","cited_by_count":2,"area":null},{"id":"2406.09140","title":"Investigating the translation capabilities of Large Language Models trained on parallel data only","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2408.01394","title":"Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features","created":"2024-08-02","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":"2105.03432","title":"Generalising Multilingual Concept-to-Text NLG with Language Agnostic Delexicalisation","created":"2021-05-07","cited_by_count":1,"area":null},{"id":"2111.13284","title":"Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs","created":"2021-11-26","cited_by_count":1,"area":"distill"},{"id":"2204.12165","title":"When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?","created":"2022-04-26","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":"2210.11628","title":"Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?","created":"2022-10-20","cited_by_count":1,"area":null},{"id":"2210.11670","title":"SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Models","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2303.18011","title":"Exploiting Multilingualism in Low-resource Neural Machine Translation via Adversarial Learning","created":"2023-03-31","cited_by_count":1,"area":null},{"id":"2406.02876","title":"LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2410.04147","title":"Can the Variation of Model Weights be used as a Criterion for Self-Paced Multilingual NMT?","created":"2024-10-05","cited_by_count":1,"area":null},{"id":"2502.04537","title":"Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation","created":"2025-02-06","cited_by_count":1,"area":"distill"},{"id":"2107.09622","title":"More Parameters? No Thanks!","created":"2021-07-20","cited_by_count":0,"area":null},{"id":"2110.00712","title":"Improving Zero-shot Multilingual Neural Machine Translation for Low-Resource Languages","created":"2021-10-02","cited_by_count":0,"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}],"next_cursor":"100"}