{"list":"other","total":66,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"1801.07593","title":"Mitigating Unwanted Biases with Adversarial Learning","created":"2018-01-22","cited_by_count":663},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"1911.03894","title":"CamemBERT: a Tasty French Language Model","created":"2019-11-10","cited_by_count":368},{"id":"1802.06309","title":"Learning Adversarially Fair and Transferable Representations","created":"2018-02-17","cited_by_count":353},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2012.15613","title":"How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models","created":"2020-12-31","cited_by_count":318},{"id":"1407.6981","title":"RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response","created":"2014-07-25","cited_by_count":272},{"id":"2012.05345","title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research","created":"2020-12-09","cited_by_count":260},{"id":"1904.03310","title":"Gender Bias in Contextualized Word Embeddings","created":"2019-04-05","cited_by_count":203},{"id":"2004.00053","title":"Information Leakage in Embedding Models","created":"2020-03-31","cited_by_count":203},{"id":"1907.04307","title":"Multilingual Universal Sentence Encoder for Semantic Retrieval","created":"2019-07-09","cited_by_count":193},{"id":"1906.11798","title":"Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference","created":"2019-06-27","cited_by_count":175},{"id":"1808.06640","title":"Adversarial Removal of Demographic Attributes from Text Data","created":"2018-08-20","cited_by_count":170},{"id":"1709.07886","title":"Machine Learning Models that Remember Too Much","created":"2017-09-22","cited_by_count":169},{"id":"1809.01496","title":"Learning Gender-Neutral Word Embeddings","created":"2018-08-29","cited_by_count":169},{"id":"1903.05987","title":"To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks","created":"2019-03-14","cited_by_count":167},{"id":"2010.02353","title":"Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages","created":"2020-10-05","cited_by_count":159},{"id":"1912.05372","title":"FlauBERT: Unsupervised Language Model Pre-training for French","created":"2019-12-11","cited_by_count":153},{"id":"2010.10906","title":"German's Next Language Model","created":"2020-10-21","cited_by_count":144},{"id":"2006.06202","title":"A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages","created":"2020-06-11","cited_by_count":131},{"id":"1804.06323","title":"When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?","created":"2018-04-17","cited_by_count":126},{"id":"1910.08902","title":"Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations","created":"2019-10-20","cited_by_count":119},{"id":"1912.07076","title":"Multilingual is not enough: BERT for Finnish","created":"2019-12-15","cited_by_count":119},{"id":"1806.04313","title":"Embedding Text in Hyperbolic Spaces","created":"2018-06-12","cited_by_count":76},{"id":"1805.06093","title":"Towards Robust and Privacy-preserving Text Representations","created":"2018-05-16","cited_by_count":75},{"id":"2005.00636","title":"We Need to Talk About Random Splits","created":"2020-05-01","cited_by_count":71},{"id":"2010.01285","title":"Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness","created":"2020-10-03","cited_by_count":67},{"id":"1906.00742","title":"Gender-preserving Debiasing for Pre-trained Word Embeddings","created":"2019-06-03","cited_by_count":61},{"id":"1602.07387","title":"Discrete Distribution Estimation under Local Privacy","created":"2016-02-24","cited_by_count":59},{"id":"1808.09408","title":"Privacy-preserving Neural Representations of Text","created":"2018-08-28","cited_by_count":54},{"id":"1811.10256","title":"Generalised Differential Privacy for Text Document Processing","created":"2018-11-26","cited_by_count":52},{"id":"1910.08917","title":"Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text","created":"2019-10-20","cited_by_count":50},{"id":"1908.02997","title":"Local Differential Privacy for Deep Learning","created":"2019-08-08","cited_by_count":46},{"id":"2107.07928","title":"TEM: High Utility Metric Differential Privacy on Text","created":"2021-07-16","cited_by_count":43},{"id":"2010.11947","title":"A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metric","created":"2020-10-22","cited_by_count":42},{"id":"2010.05609","title":"Load What You Need: Smaller Versions of Multilingual BERT","created":"2020-10-12","cited_by_count":32},{"id":"1910.03806","title":"Is Multilingual BERT Fluent in Language Generation?","created":"2019-10-09","cited_by_count":28},{"id":"1910.13212","title":"Privacy Enhanced Multimodal Neural Representations for Emotion Recognition","created":"2019-10-29","cited_by_count":22},{"id":"2108.12318","title":"CAPE: Context-Aware Private Embeddings for Private Language Learning","created":"2021-08-27","cited_by_count":22},{"id":"1911.01533","title":"Speaker-invariant Affective Representation Learning via Adversarial Training","created":"2019-11-04","cited_by_count":14},{"id":"2101.11310","title":"Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling","created":"2021-01-27","cited_by_count":13},{"id":"1907.03189","title":"I Am Not What I Write: Privacy Preserving Text Representation Learning","created":"2019-07-06","cited_by_count":12},{"id":"2010.04658","title":"Case Study: Deontological Ethics in NLP","created":"2020-10-09","cited_by_count":12},{"id":"2011.01136","title":"Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation","created":"2020-11-02","cited_by_count":9},{"id":"1804.04095","title":"Predicting Twitter User Socioeconomic Attributes with Network and Language Information","created":"2018-04-11","cited_by_count":8},{"id":"2108.10640","title":"Are the Multilingual Models Better? Improving Czech Sentiment with Transformers","created":"2021-08-24","cited_by_count":7},{"id":"1405.7418","title":"Deanonymisation of clients in Bitcoin P2P network","created":"2014-05-28","cited_by_count":5},{"id":"1503.00756","title":"Constructing elastic distinguishability metrics for location privacy","created":"2015-03-02","cited_by_count":5},{"id":"1912.01116","title":"Long Distance Relationships without Time Travel: Boosting the Performance of a Sparse Predictive Autoencoder in Sequence Modeling","created":"2019-12-02","cited_by_count":2},{"id":"1806.02701","title":"There goes Wally: Anonymously sharing your location gives you away","created":"2018-06-07","cited_by_count":1},{"id":"1912.06895","title":"Deep Poisoning: Towards Robust Image Data Sharing against Visual Disclosure","created":"2019-12-14","cited_by_count":1},{"id":"2109.01211","title":"Quantifying Reproducibility in NLP and ML","created":"2021-09-02","cited_by_count":1}],"next_cursor":null}