{"total":21,"rows":[{"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":"2112.07790","title":"Maximum Bayes Smatch Ensemble Distillation for AMR Parsing","created":"2021-12-14","cited_by_count":29,"area":null},{"id":"2103.05070","title":"Text Simplification by Tagging","created":"2021-03-08","cited_by_count":27,"area":null},{"id":"2401.02994","title":"Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM","created":"2024-01-04","cited_by_count":27,"area":null},{"id":"2204.03939","title":"GigaST: A 10,000-hour Pseudo Speech Translation Corpus","created":"2022-04-08","cited_by_count":20,"area":null},{"id":"2205.14333","title":"One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation","created":"2022-05-28","cited_by_count":20,"area":null},{"id":"2306.05317","title":"CUED at ProbSum 2023: Hierarchical Ensemble of Summarization Models","created":"2023-06-08","cited_by_count":8,"area":null},{"id":"2109.10485","title":"The NiuTrans Machine Translation Systems for WMT21","created":"2021-09-22","cited_by_count":4,"area":null},{"id":"2112.08670","title":"Amortized Noisy Channel Neural Machine Translation","created":"2021-12-16","cited_by_count":4,"area":null},{"id":"2205.09273","title":"Twist Decoding: Diverse Generators Guide Each Other","created":"2022-05-19","cited_by_count":4,"area":null},{"id":"2309.06520","title":"Minimum Bayes' Risk Decoding for System Combination of Grammatical Error Correction Systems","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2105.07319","title":"The Volctrans Neural Speech Translation System for IWSLT 2021","created":"2021-05-16","cited_by_count":3,"area":null},{"id":"2306.09380","title":"Understanding Parameter Sharing in Transformers","created":"2023-06-15","cited_by_count":3,"area":null},{"id":"2104.00664","title":"Sampling and Filtering of Neural Machine Translation Distillation Data","created":"2021-04-01","cited_by_count":2,"area":null},{"id":"2106.10002","title":"Recurrent Stacking of Layers in Neural Networks: An Application to Neural Machine Translation","created":"2021-06-18","cited_by_count":1,"area":null},{"id":"2305.06155","title":"Leveraging Synthetic Targets for Machine Translation","created":"2023-05-07","cited_by_count":1,"area":null},{"id":"2403.00144","title":"EBBS: An Ensemble with Bi-Level Beam Search for Zero-Shot Machine Translation","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2409.01420","title":"Erasure Coded Neural Network Inference via Fisher Averaging","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2305.11808","title":"Pseudo-Label Training and Model Inertia in Neural Machine Translation","created":"2023-05-19","cited_by_count":0,"area":null},{"id":"2401.16055","title":"Stolen Subwords: Importance of Vocabularies for Machine Translation Model Stealing","created":"2024-01-29","cited_by_count":0,"area":null},{"id":"2408.11327","title":"Plug, Play, and Fuse: Zero-Shot Joint Decoding via Word-Level Re-ranking Across Diverse Vocabularies","created":"2024-08-21","cited_by_count":0,"area":null}],"next_cursor":null}