{"list":"other","total":58,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"1603.01360","title":"Neural Architectures for Named Entity Recognition","created":"2016-03-04","cited_by_count":550},{"id":"1508.01991","title":"Bidirectional LSTM-CRF Models for Sequence Tagging","created":"2015-08-09","cited_by_count":546},{"id":"1803.11175","title":"Universal Sentence Encoder","created":"2018-03-29","cited_by_count":489},{"id":"2003.00104","title":"AraBERT: Transformer-based Model for Arabic Language Understanding","created":"2020-02-28","cited_by_count":362},{"id":"1603.01354","title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","created":"2016-03-04","cited_by_count":341},{"id":"1906.05714","title":"A Multiscale Visualization of Attention in the Transformer Model","created":"2019-06-12","cited_by_count":292},{"id":"1911.03852","title":"HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks","created":"2019-11-10","cited_by_count":261},{"id":"1905.00546","title":"Billion-scale semi-supervised learning for image classification","created":"2019-05-02","cited_by_count":232},{"id":"1805.06201","title":"Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations","created":"2018-05-16","cited_by_count":201},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"1907.04307","title":"Multilingual Universal Sentence Encoder for Semantic Retrieval","created":"2019-07-09","cited_by_count":193},{"id":"2002.08307","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","created":"2020-02-19","cited_by_count":185},{"id":"2003.02245","title":"Data Augmentation using Pre-trained Transformer Models","created":"2020-03-04","cited_by_count":168},{"id":"1404.2188","title":"A Convolutional Neural Network for Modelling Sentences","created":"2014-04-08","cited_by_count":163},{"id":"1808.08949","title":"Dissecting Contextual Word Embeddings: Architecture and Representation","created":"2018-08-27","cited_by_count":146},{"id":"1405.3531","title":"Return of the Devil in the Details: Delving Deep into Convolutional Nets","created":"2014-05-14","cited_by_count":122},{"id":"1910.11470","title":"A Survey on Recent Advances in Named Entity Recognition from Deep Learning models","created":"2019-10-25","cited_by_count":117},{"id":"2004.12376","title":"GLUECoS : An Evaluation Benchmark for Code-Switched NLP","created":"2020-04-26","cited_by_count":102},{"id":"2005.04322","title":"LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation","created":"2020-05-09","cited_by_count":93},{"id":"1709.01643","title":"Learning to Compose Domain-Specific Transformations for Data Augmentation","created":"2017-09-06","cited_by_count":91},{"id":"1705.00108","title":"Semi-supervised sequence tagging with bidirectional language models","created":"2017-04-29","cited_by_count":86},{"id":"1803.07416","title":"Tensor2Tensor for Neural Machine Translation","created":"2018-03-16","cited_by_count":85},{"id":"1702.01923","title":"Comparative Study of CNN and RNN for Natural Language Processing","created":"2017-02-07","cited_by_count":82},{"id":"1806.03852","title":"Data augmentation instead of explicit regularization","created":"2018-06-11","cited_by_count":63},{"id":"1904.11643","title":"Bayesian Generative Active Deep Learning","created":"2019-04-26","cited_by_count":57},{"id":"1906.05394","title":"Neural Arabic Question Answering","created":"2019-06-12","cited_by_count":48},{"id":"2011.12631","title":"A Panoramic Survey of Natural Language Processing in the Arab World","created":"2020-11-25","cited_by_count":45},{"id":"1909.13016","title":"Overview for the Second Shared Task on Language Identification in Code-Switched Data","created":"2019-09-28","cited_by_count":33},{"id":"1712.02029","title":"AdaBatch: Adaptive Batch Sizes for Training Deep Neural Networks","created":"2017-12-06","cited_by_count":29},{"id":"2006.10414","title":"Multi-Encoder-Decoder Transformer for Code-Switching Speech Recognition","created":"2020-06-18","cited_by_count":28},{"id":"2003.10555","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","created":"2020-03-23","cited_by_count":27},{"id":"1906.04138","title":"Named Entity Recognition on Code-Switched Data: Overview of the CALCS 2018 Shared Task","created":"2019-06-10","cited_by_count":24},{"id":"1610.02213","title":"Challenges of Computational Processing of Code-Switching","created":"2016-10-07","cited_by_count":20},{"id":"1404.4641","title":"Multilingual Models for Compositional Distributed Semantics","created":"2014-04-17","cited_by_count":18},{"id":"1404.5367","title":"Lexicon Infused Phrase Embeddings for Named Entity Resolution","created":"2014-04-22","cited_by_count":16},{"id":"2005.09117","title":"Contextual Embeddings: When Are They Worth It?","created":"2020-05-18","cited_by_count":15},{"id":"1804.06024","title":"Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages","created":"2018-04-17","cited_by_count":13},{"id":"1604.00425","title":"Cross-lingual Models of Word Embeddings: An Empirical Comparison","created":"2016-04-01","cited_by_count":12},{"id":"1904.01989","title":"Subword-Level Language Identification for Intra-Word Code-Switching","created":"2019-04-03","cited_by_count":12},{"id":"1909.11241","title":"Atalaya at TASS 2019: Data Augmentation and Robust Embeddings for Sentiment Analysis","created":"2019-09-25","cited_by_count":12},{"id":"1703.03091","title":"Deep Learning applied to NLP","created":"2017-03-09","cited_by_count":11},{"id":"1810.04142","title":"A Fast, Compact, Accurate Model for Language Identification of Codemixed Text","created":"2018-10-09","cited_by_count":11},{"id":"1904.02954","title":"Alternative Weighting Schemes for ELMo Embeddings","created":"2019-04-05","cited_by_count":7},{"id":"1906.00282","title":"Biomedical Named Entity Recognition via Reference-Set Augmented Bootstrapping","created":"2019-06-01","cited_by_count":4},{"id":"1412.4314","title":"Recurrent-Neural-Network for Language Detection on Twitter Code-Switching Corpus","created":"2014-12-14","cited_by_count":3},{"id":"1804.05630","title":"Arabic Named Entity Recognition using Word Representations","created":"2018-04-16","cited_by_count":1}],"next_cursor":null}