{"list":"other","total":52,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"1412.6575","title":"Embedding Entities and Relations for Learning and Inference in Knowledge Bases","created":"2014-12-20","cited_by_count":932},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1606.06357","title":"Complex Embeddings for Simple Link Prediction","created":"2016-06-20","cited_by_count":902},{"id":"1902.10197","title":"RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space","created":"2019-02-26","cited_by_count":898},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"1707.01476","title":"Convolutional 2D Knowledge Graph Embeddings","created":"2017-07-05","cited_by_count":730},{"id":"1906.05317","title":"COMET: Commonsense Transformers for Automatic Knowledge Graph Construction","created":"2019-06-12","cited_by_count":450},{"id":"1911.06136","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","created":"2019-11-13","cited_by_count":356},{"id":"1909.03193","title":"KG-BERT: BERT for Knowledge Graph Completion","created":"2019-09-07","cited_by_count":324},{"id":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320},{"id":"2106.06935","title":"Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction","created":"2021-06-13","cited_by_count":275},{"id":"1503.00759","title":"A Review of Relational Machine Learning for Knowledge Graphs","created":"2015-03-02","cited_by_count":265},{"id":"1911.06962","title":"Inductive Relation Prediction by Subgraph Reasoning","created":"2019-11-16","cited_by_count":239},{"id":"1802.04868","title":"SimplE Embedding for Link Prediction in Knowledge Graphs","created":"2018-02-13","cited_by_count":195},{"id":"2212.00959","title":"UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph","created":"2022-12-02","cited_by_count":103},{"id":"2203.00274","title":"TableFormer: Robust Transformer Modeling for Table-Text Encoding","created":"2022-03-01","cited_by_count":91},{"id":"2203.10321","title":"Sequence-to-Sequence Knowledge Graph Completion and Question Answering","created":"2022-03-19","cited_by_count":75},{"id":"2106.12144","title":"NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs","created":"2021-06-23","cited_by_count":72},{"id":"1906.07241","title":"Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modeling","created":"2019-06-17","cited_by_count":71},{"id":"2102.10249","title":"Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction","created":"2021-02-20","cited_by_count":68},{"id":"1711.03438","title":"Open-World Knowledge Graph Completion","created":"2017-11-09","cited_by_count":64},{"id":"2010.03496","title":"Inductive Entity Representations from Text via Link Prediction","created":"2020-10-07","cited_by_count":62},{"id":"1910.02915","title":"Commonsense Knowledge Base Completion with Structural and Semantic Context","created":"2019-10-07","cited_by_count":61},{"id":"2002.06757","title":"Relational Message Passing for Knowledge Graph Completion","created":"2020-02-17","cited_by_count":61},{"id":"1911.02707","title":"Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs","created":"2019-11-07","cited_by_count":59},{"id":"2106.10502","title":"JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs","created":"2021-06-19","cited_by_count":58},{"id":"2306.11489","title":"Give Us the Facts: Enhancing Large Language Models with Knowledge Graphs for Fact-aware Language Modeling","created":"2023-06-20","cited_by_count":56},{"id":"2008.12813","title":"HittER: Hierarchical Transformers for Knowledge Graph Embeddings","created":"2020-08-28","cited_by_count":54},{"id":"1811.01399","title":"Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding","created":"2018-11-04","cited_by_count":53},{"id":"2210.00105","title":"A Decade of Knowledge Graphs in Natural Language Processing: A Survey","created":"2022-09-30","cited_by_count":40},{"id":"1808.07018","title":"Hypernetwork Knowledge Graph Embeddings","created":"2018-08-21","cited_by_count":38},{"id":"1711.05435","title":"TorusE: Knowledge Graph Embedding on a Lie Group","created":"2017-11-15","cited_by_count":36},{"id":"2103.07102","title":"Inductive Relation Prediction by BERT","created":"2021-03-12","cited_by_count":27},{"id":"2003.13118","title":"Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement","created":"2020-03-29","cited_by_count":20},{"id":"1906.08382","title":"An Open-World Extension to Knowledge Graph Completion Models","created":"2019-06-19","cited_by_count":16},{"id":"1911.03561","title":"Graph-to-Graph Transformer for Transition-based Dependency Parsing","created":"2019-11-08","cited_by_count":13},{"id":"2109.00840","title":"Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning","created":"2021-09-02","cited_by_count":9},{"id":"2009.12765","title":"Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational Assumptions","created":"2020-09-27","cited_by_count":7},{"id":"2203.16574","title":"Graph Refinement for Coreference Resolution","created":"2022-03-30","cited_by_count":7},{"id":"2310.17936","title":"Transformers as Graph-to-Graph Models","created":"2023-10-27","cited_by_count":5},{"id":"2310.14708","title":"Strong and Efficient Baselines for Open Domain Conversational Question Answering","created":"2023-10-23","cited_by_count":2}],"next_cursor":null}