{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"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":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"id":"1312.6184","title":"Do Deep Nets Really Need to be Deep?","created":"2013-12-21","cited_by_count":474},{"id":"1711.02281","title":"Non-Autoregressive Neural Machine Translation","created":"2017-11-07","cited_by_count":463},{"id":"1609.07152","title":"Input Convex Neural Networks","created":"2016-09-22","cited_by_count":414},{"id":"1912.03263","title":"Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One","created":"2019-12-06","cited_by_count":405},{"id":"1603.01354","title":"End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF","created":"2016-03-04","cited_by_count":341},{"id":"1802.06901","title":"Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement","created":"2018-02-19","cited_by_count":195},{"id":"1604.04382","title":"Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks","created":"2016-04-15","cited_by_count":192},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"1606.02960","title":"Sequence-to-Sequence Learning as Beam-Search Optimization","created":"2016-06-09","cited_by_count":127},{"id":"1911.02727","title":"Understanding Knowledge Distillation in Non-autoregressive Machine Translation","created":"2019-11-07","cited_by_count":122},{"id":"1609.03126","title":"Energy-based Generative Adversarial Network","created":"2016-09-11","cited_by_count":119},{"id":"1803.03382","title":"Fast Decoding in Sequence Models using Discrete Latent Variables","created":"2018-03-09","cited_by_count":104},{"id":"2004.07437","title":"Non-Autoregressive Machine Translation with Latent Alignments","created":"2020-04-16","cited_by_count":96},{"id":"1909.02480","title":"FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow","created":"2019-09-05","cited_by_count":89},{"id":"1811.04719","title":"End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification","created":"2018-11-12","cited_by_count":72},{"id":"2004.01655","title":"Aligned Cross Entropy for Non-Autoregressive Machine Translation","created":"2020-04-03","cited_by_count":65},{"id":"1511.06350","title":"Structured Prediction Energy Networks","created":"2015-11-19","cited_by_count":59},{"id":"1910.11555","title":"Fast Structured Decoding for Sequence Models","created":"2019-10-25","cited_by_count":59},{"id":"1911.09320","title":"Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation","created":"2019-11-21","cited_by_count":40},{"id":"1906.02041","title":"Imitation Learning for Non-Autoregressive Neural Machine Translation","created":"2019-06-05","cited_by_count":36},{"id":"1703.05667","title":"End-to-End Learning for Structured Prediction Energy Networks","created":"2017-03-16","cited_by_count":33},{"id":"1702.02429","title":"Trainable Greedy Decoding for Neural Machine Translation","created":"2017-02-08","cited_by_count":23},{"id":"1602.06701","title":"Inference Networks for Sequential Monte Carlo in Graphical Models","created":"2016-02-22","cited_by_count":20},{"id":"1404.5367","title":"Lexicon Infused Phrase Embeddings for Named Entity Resolution","created":"2014-04-22","cited_by_count":16},{"id":"1701.02854","title":"Towards Decoding as Continuous Optimization in Neural Machine Translation","created":"2017-01-11","cited_by_count":15},{"id":"1702.01691","title":"Calibrating Energy-based Generative Adversarial Networks","created":"2017-02-06","cited_by_count":13},{"id":"1803.03376","title":"Learning Approximate Inference Networks for Structured Prediction","created":"2018-03-09","cited_by_count":13},{"id":"2001.05136","title":"Non-Autoregressive Machine Translation with Disentangled Context Transformer","created":"2020-01-15","cited_by_count":13},{"id":"1804.07915","title":"A Stable and Effective Learning Strategy for Trainable Greedy Decoding","created":"2018-04-21","cited_by_count":12},{"id":"1811.00539","title":"Deep Structured Prediction with Nonlinear Output Transformations","created":"2018-11-01","cited_by_count":12},{"id":"1609.07561","title":"Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser","created":"2016-09-24","cited_by_count":11},{"id":"1708.00111","title":"A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models","created":"2017-08-01","cited_by_count":10},{"id":"1910.14670","title":"Graph Structured Prediction Energy Networks","created":"2019-10-31","cited_by_count":10},{"id":"1804.02009","title":"Regularizing Deep Networks by Modeling and Predicting Label Structure","created":"2018-04-05","cited_by_count":9},{"id":"1511.06433","title":"Blending LSTMs into CNNs","created":"2015-11-19","cited_by_count":7},{"id":"1807.00993","title":"Improved training of neural trans-dimensional random field language models with dynamic noise-contrastive estimation","created":"2018-07-03","cited_by_count":5},{"id":"2004.10188","title":"Residual Energy-Based Models for Text","created":"2020-04-06","cited_by_count":5},{"id":"1706.02807","title":"Learning to Embed Words in Context for Syntactic Tasks","created":"2017-06-09","cited_by_count":1},{"id":"1811.01382","title":"Neural CRF transducers for sequence labeling","created":"2018-11-04","cited_by_count":1}],"next_cursor":null}