{"list":"other","total":55,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"1511.05493","title":"Gated Graph Sequence Neural Networks","created":"2015-11-17","cited_by_count":796},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2007.12626","title":"SummEval: Re-evaluating Summarization Evaluation","created":"2020-07-24","cited_by_count":674},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"1509.00685","title":"A Neural Attention Model for Abstractive Sentence Summarization","created":"2015-09-02","cited_by_count":396},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"1905.02450","title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","created":"2019-05-07","cited_by_count":347},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"1703.04394","title":"Zero-Shot Learning -- The Good, the Bad and the Ugly","created":"2017-03-13","cited_by_count":255},{"id":"1711.00740","title":"Learning to Represent Programs with Graphs","created":"2017-11-01","cited_by_count":220},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192},{"id":"1907.12461","title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks","created":"2019-07-29","cited_by_count":182},{"id":"1808.10792","title":"Bottom-Up Abstractive Summarization","created":"2018-08-31","cited_by_count":177},{"id":"2005.00653","title":"A Transformer-based Approach for Source Code Summarization","created":"2020-05-01","cited_by_count":133},{"id":"2005.00628","title":"Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?","created":"2020-05-01","cited_by_count":127},{"id":"1601.04811","title":"Modeling Coverage for Neural Machine Translation","created":"2016-01-19","cited_by_count":110},{"id":"1811.07234","title":"Improving Automatic Source Code Summarization via Deep Reinforcement Learning","created":"2018-11-17","cited_by_count":100},{"id":"2006.05405","title":"Retrieval-Augmented Generation for Code Summarization via Hybrid GNN","created":"2020-06-09","cited_by_count":89},{"id":"1902.01954","title":"A Neural Model for Generating Natural Language Summaries of Program Subroutines","created":"2019-02-05","cited_by_count":77},{"id":"2007.04973","title":"Contrastive Code Representation Learning","created":"2020-07-09","cited_by_count":76},{"id":"1904.01172","title":"Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches","created":"2019-04-02","cited_by_count":65},{"id":"1706.09799","title":"Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation","created":"2017-06-29","cited_by_count":61},{"id":"1911.03868","title":"Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering","created":"2019-11-10","cited_by_count":59},{"id":"2003.10687","title":"Felix: Flexible Text Editing Through Tagging and Insertion","created":"2020-03-24","cited_by_count":58},{"id":"2002.05442","title":"Deep Learning for Source Code Modeling and Generation: Models, Applications and Challenges","created":"2020-02-13","cited_by_count":55},{"id":"2005.03393","title":"Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation","created":"2020-05-07","cited_by_count":34},{"id":"1803.09544","title":"A General Path-Based Representation for Predicting Program Properties","created":"2018-03-26","cited_by_count":29},{"id":"2010.01410","title":"Code to Comment \"Translation\": Data, Metrics, Baselining & Evaluation","created":"2020-10-03","cited_by_count":29},{"id":"2012.14710","title":"Code Summarization with Structure-induced Transformer","created":"2020-12-29","cited_by_count":29},{"id":"2010.01694","title":"On Losses for Modern Language Models","created":"2020-10-04","cited_by_count":21},{"id":"2103.07845","title":"Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting","created":"2021-03-14","cited_by_count":19},{"id":"1909.04352","title":"Automatic Code Summarization: A Systematic Literature Review","created":"2019-09-10","cited_by_count":18},{"id":"2107.00992","title":"Multimodal Representation for Neural Code Search","created":"2021-07-02","cited_by_count":11},{"id":"1807.02301","title":"Sequential Copying Networks","created":"2018-07-06","cited_by_count":10},{"id":"1811.08318","title":"Self-Organizing Maps for Storage and Transfer of Knowledge in Reinforcement Learning","created":"2018-11-18","cited_by_count":8},{"id":"1905.05251","title":"Learning Scalable and Precise Representation of Program Semantics","created":"2019-05-13","cited_by_count":6},{"id":"1907.02136","title":"Learning Blended, Precise Semantic Program Embeddings","created":"2019-07-03","cited_by_count":5}],"next_cursor":null}