{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1612.03651","title":"FastText.zip: Compressing text classification models","created":"2016-12-12","cited_by_count":335},{"id":"2008.00401","title":"Multilingual Translation with Extensible Multilingual Pretraining and Finetuning","created":"2020-08-02","cited_by_count":287},{"id":"2004.11867","title":"Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation","created":"2020-04-24","cited_by_count":277},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"1906.00591","title":"Evaluating Gender Bias in Machine Translation","created":"2019-06-03","cited_by_count":249},{"id":"1903.00089","title":"Massively Multilingual Neural Machine Translation","created":"2019-02-28","cited_by_count":246},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"2004.09602","title":"Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation","created":"2020-04-20","cited_by_count":188},{"id":"2203.05740","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","created":"2022-03-11","cited_by_count":180},{"id":"2203.00555","title":"DeepNet: Scaling Transformers to 1,000 Layers","created":"2022-03-01","cited_by_count":178},{"id":"1911.04944","title":"CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB","created":"2019-11-10","cited_by_count":177},{"id":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"2104.06683","title":"The Curious Case of Hallucinations in Neural Machine Translation","created":"2021-04-14","cited_by_count":161},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141},{"id":"1911.06154","title":"CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs","created":"2019-11-10","cited_by_count":136},{"id":"2109.03646","title":"Sustainable Modular Debiasing of Language Models","created":"2021-09-08","cited_by_count":100},{"id":"2105.00572","title":"Larger-Scale Transformers for Multilingual Masked Language Modeling","created":"2021-05-02","cited_by_count":87},{"id":"2203.10705","title":"Compression of Generative Pre-trained Language Models via Quantization","created":"2022-03-21","cited_by_count":79},{"id":"2006.05754","title":"Gender in Danger? Evaluating Speech Translation Technology on the MuST-SHE Corpus","created":"2020-06-10","cited_by_count":57},{"id":"2101.09688","title":"Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models","created":"2021-01-24","cited_by_count":57},{"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},{"id":"2105.12967","title":"Selective Knowledge Distillation for Neural Machine Translation","created":"2021-05-27","cited_by_count":43},{"id":"2109.03228","title":"Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression","created":"2021-09-07","cited_by_count":38},{"id":"1802.00150","title":"Alternating Multi-bit Quantization for Recurrent Neural Networks","created":"2018-02-01","cited_by_count":31},{"id":"2106.00169","title":"Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation","created":"2021-06-01","cited_by_count":28},{"id":"2203.09866","title":"Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation","created":"2022-03-18","cited_by_count":23},{"id":"2012.13866","title":"Learning Light-Weight Translation Models from Deep Transformer","created":"2020-12-27","cited_by_count":22},{"id":"2010.06018","title":"Gender Coreference and Bias Evaluation at WMT 2020","created":"2020-10-12","cited_by_count":21},{"id":"2204.01397","title":"A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems","created":"2022-04-04","cited_by_count":15},{"id":"2203.15996","title":"TextPruner: A Model Pruning Toolkit for Pre-Trained Language Models","created":"2022-03-30","cited_by_count":10},{"id":"2105.14940","title":"Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?","created":"2021-05-31","cited_by_count":6},{"id":"1806.09089","title":"Character-Level Feature Extraction with Densely Connected Networks","created":"2018-06-24","cited_by_count":3}],"next_cursor":null}