{"list":"other","total":62,"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"1602.02068","title":"From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification","created":"2016-02-05","cited_by_count":341},{"id":"1503.00075","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","created":"2015-02-28","cited_by_count":306},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1903.05662","title":"Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets","created":"2019-03-13","cited_by_count":231},{"id":"1606.01933","title":"A Decomposable Attention Model for Natural Language Inference","created":"2016-06-06","cited_by_count":215},{"id":"1609.06038","title":"Enhanced LSTM for Natural Language Inference","created":"2016-09-20","cited_by_count":200},{"id":"1905.05702","title":"Sparse Sequence-to-Sequence Models","created":"2019-05-14","cited_by_count":170},{"id":"1411.0030","title":"A* Sampling","created":"2014-10-31","cited_by_count":151},{"id":"1703.04826","title":"Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling","created":"2017-03-14","cited_by_count":137},{"id":"1804.06028","title":"ListOps: A Diagnostic Dataset for Latent Tree Learning","created":"2018-04-17","cited_by_count":129},{"id":"1905.08160","title":"Interpretable Neural Predictions with Differentiable Binary Variables","created":"2019-05-20","cited_by_count":126},{"id":"1702.00953","title":"Deep Learning with Low Precision by Half-wave Gaussian Quantization","created":"2017-02-03","cited_by_count":117},{"id":"1602.07776","title":"Recurrent Neural Network Grammars","created":"2016-02-25","cited_by_count":109},{"id":"1609.01704","title":"Hierarchical Multiscale Recurrent Neural Networks","created":"2016-09-06","cited_by_count":104},{"id":"1702.00887","title":"Structured Attention Networks","created":"2017-02-03","cited_by_count":95},{"id":"1611.01587","title":"A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks","created":"2016-11-05","cited_by_count":62},{"id":"1802.04223","title":"SparseMAP: Differentiable Sparse Structured Inference","created":"2018-02-12","cited_by_count":62},{"id":"1808.10122","title":"Learning Neural Templates for Text Generation","created":"2018-08-30","cited_by_count":61},{"id":"1904.02142","title":"Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders","created":"2019-04-03","cited_by_count":60},{"id":"1802.03676","title":"Differentiable Dynamic Programming for Structured Prediction and Attention","created":"2018-02-11","cited_by_count":58},{"id":"1711.02013","title":"Neural Language Modeling by Jointly Learning Syntax and Lexicon","created":"2017-11-02","cited_by_count":57},{"id":"1707.02786","title":"Learning to Compose Task-Specific Tree Structures","created":"2017-07-10","cited_by_count":48},{"id":"1904.03746","title":"Unsupervised Recurrent Neural Network Grammars","created":"2019-04-07","cited_by_count":47},{"id":"1606.02892","title":"Linguistic Input Features Improve Neural Machine Translation","created":"2016-06-09","cited_by_count":38},{"id":"1705.07704","title":"A Regularized Framework for Sparse and Structured Neural Attention","created":"2017-05-22","cited_by_count":38},{"id":"1603.06021","title":"A Fast Unified Model for Parsing and Sentence Understanding","created":"2016-03-19","cited_by_count":34},{"id":"1611.09100","title":"Learning to Compose Words into Sentences with Reinforcement Learning","created":"2016-11-28","cited_by_count":30},{"id":"1603.06075","title":"Tree-to-Sequence Attentional Neural Machine Translation","created":"2016-03-19","cited_by_count":28},{"id":"1609.07317","title":"Language as a Latent Variable: Discrete Generative Models for Sentence Compression","created":"2016-09-23","cited_by_count":28},{"id":"1902.09393","title":"Cooperative Learning of Disjoint Syntax and Semantics","created":"2019-02-25","cited_by_count":27},{"id":"1511.06411","title":"Training Deep Neural Networks via Direct Loss Minimization","created":"2015-11-19","cited_by_count":25},{"id":"1705.09189","title":"Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs","created":"2017-05-25","cited_by_count":24},{"id":"1705.09207","title":"Learning Structured Text Representations","created":"2017-05-25","cited_by_count":24},{"id":"1806.07832","title":"StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing","created":"2018-06-20","cited_by_count":22},{"id":"1807.09875","title":"Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational Autoencoder","created":"2018-07-25","cited_by_count":19},{"id":"2107.00967","title":"R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling","created":"2021-07-02","cited_by_count":19},{"id":"2012.05395","title":"Infusing Finetuning with Semantic Dependencies","created":"2020-12-10","cited_by_count":18},{"id":"2001.04437","title":"LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction","created":"2020-01-13","cited_by_count":17},{"id":"1808.09644","title":"On Tree-Based Neural Sentence Modeling","created":"2018-08-29","cited_by_count":16},{"id":"2007.00266","title":"Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering","created":"2020-07-01","cited_by_count":16},{"id":"1805.04658","title":"Backpropagating through Structured Argmax using a SPIGOT","created":"2018-05-12","cited_by_count":11},{"id":"1704.01691","title":"Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction","created":"2017-04-06","cited_by_count":9},{"id":"1411.1147","title":"Conditional Random Field Autoencoders for Unsupervised Structured Prediction","created":"2014-11-05","cited_by_count":8},{"id":"2010.04361","title":"Event Representation with Sequential, Semi-Supervised Discrete Variables","created":"2020-10-09","cited_by_count":8},{"id":"1806.00840","title":"Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing","created":"2018-06-03","cited_by_count":7},{"id":"1906.09992","title":"Learning Latent Trees with Stochastic Perturbations and Differentiable Dynamic Programming","created":"2019-06-24","cited_by_count":7},{"id":"2010.02357","title":"Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning","created":"2020-10-05","cited_by_count":6},{"id":"2109.05112","title":"Improved Latent Tree Induction with Distant Supervision via Span Constraints","created":"2021-09-10","cited_by_count":6},{"id":"2106.01580","title":"The Limitations of Limited Context for Constituency Parsing","created":"2021-06-03","cited_by_count":5},{"id":"1805.10850","title":"Inducing Grammars with and for Neural Machine Translation","created":"2018-05-28","cited_by_count":3},{"id":"1809.00653","title":"Towards Dynamic Computation Graphs via Sparse Latent Structure","created":"2018-09-03","cited_by_count":2}],"next_cursor":null}