{"list":"other","total":59,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1705.07057","title":"Masked Autoregressive Flow for Density Estimation","created":"2017-05-19","cited_by_count":684},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"1606.04934","title":"Improving Variational Inference with Inverse Autoregressive Flow","created":"2016-06-15","cited_by_count":640},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"1906.04032","title":"Neural Spline Flows","created":"2019-06-10","cited_by_count":596},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1908.08345","title":"Text Summarization with Pretrained Encoders","created":"2019-08-22","cited_by_count":556},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"1804.05685","title":"A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents","created":"2018-04-16","cited_by_count":478},{"id":"1906.01749","title":"Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model","created":"2019-06-04","cited_by_count":431},{"id":"1711.01558","title":"Wasserstein Auto-Encoders","created":"2017-11-05","cited_by_count":373},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"1905.02450","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","created":"2019-05-07","cited_by_count":347},{"id":"2001.04063","title":"ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training","created":"2020-01-13","cited_by_count":222},{"id":"1907.12461","title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks","created":"2019-07-29","cited_by_count":182},{"id":"1605.06069","title":"A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues","created":"2016-05-19","cited_by_count":174},{"id":"1706.02262","title":"InfoVAE: Information Maximizing Variational Autoencoders","created":"2017-06-07","cited_by_count":124},{"id":"1901.05534","title":"Lagging Inference Networks and Posterior Collapse in Variational Autoencoders","created":"2019-01-16","cited_by_count":124},{"id":"1802.02550","title":"Semi-Amortized Variational Autoencoders","created":"2018-02-07","cited_by_count":83},{"id":"2012.14660","title":"A Theoretical Analysis of the Repetition Problem in Text Generation","created":"2020-12-29","cited_by_count":83},{"id":"1702.08139","title":"Improved Variational Autoencoders for Text Modeling using Dilated Convolutions","created":"2017-02-27","cited_by_count":81},{"id":"1803.05649","title":"Sylvester Normalizing Flows for Variational Inference","created":"2018-03-15","cited_by_count":72},{"id":"2010.13002","title":"Pre-trained Summarization Distillation","created":"2020-10-24","cited_by_count":71},{"id":"1905.10347","title":"Discrete Flows: Invertible Generative Models of Discrete Data","created":"2019-05-24","cited_by_count":68},{"id":"1911.02247","title":"Unsupervised Opinion Summarization as Copycat-Review Generation","created":"2019-11-06","cited_by_count":68},{"id":"1903.07137","title":"Topic-Guided Variational Autoencoders for Text Generation","created":"2019-03-17","cited_by_count":44},{"id":"2001.05168","title":"Invertible Generative Modeling using Linear Rational Splines","created":"2020-01-15","cited_by_count":40},{"id":"1605.07869","title":"Variational Neural Machine Translation","created":"2016-05-25","cited_by_count":35},{"id":"1702.02390","title":"A Hybrid Convolutional Variational Autoencoder for Text Generation","created":"2017-02-08","cited_by_count":33},{"id":"1801.05119","title":"Variational Recurrent Neural Machine Translation","created":"2018-01-16","cited_by_count":23},{"id":"2012.07311","title":"Topic-Oriented Spoken Dialogue Summarization for Customer Service with Saliency-Aware Topic Modeling","created":"2020-12-14","cited_by_count":23},{"id":"1805.03616","title":"A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization","created":"2018-05-09","cited_by_count":21},{"id":"2109.10616","title":"Enriching and Controlling Global Semantics for Text Summarization","created":"2021-09-22","cited_by_count":20},{"id":"1802.02032","title":"Improving Variational Encoder-Decoders in Dialogue Generation","created":"2018-02-06","cited_by_count":13},{"id":"2204.01227","title":"Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors","created":"2022-04-04","cited_by_count":13},{"id":"1807.10564","title":"Auto-Encoding Variational Neural Machine Translation","created":"2018-07-27","cited_by_count":11},{"id":"1909.13668","title":"On the Importance of the Kullback-Leibler Divergence Term in Variational Autoencoders for Text Generation","created":"2019-09-30","cited_by_count":9},{"id":"2005.13978","title":"Variational Neural Machine Translation with Normalizing Flows","created":"2020-05-28","cited_by_count":7},{"id":"1809.05233","title":"Unsupervised Abstractive Sentence Summarization using Length Controlled Variational Autoencoder","created":"2018-09-14","cited_by_count":4},{"id":"1709.07109","title":"Deconvolutional Latent-Variable Model for Text Sequence Matching","created":"2017-09-21","cited_by_count":3},{"id":"2010.10323","title":"Topic-Guided Abstractive Text Summarization: a Joint Learning Approach","created":"2020-10-20","cited_by_count":3}],"next_cursor":null}