{"list":"other","total":75,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"1802.04712","title":"Attention-based Deep Multiple Instance Learning","created":"2018-02-13","cited_by_count":1095},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"1511.05493","title":"Gated Graph Sequence Neural Networks","created":"2015-11-17","cited_by_count":796},{"id":"1405.4053","title":"Distributed Representations of Sentences and Documents","created":"2014-05-16","cited_by_count":678},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"1911.06455","title":"Graph Transformer Networks","created":"2019-11-06","cited_by_count":523},{"id":"1511.08458","title":"An Introduction to Convolutional Neural Networks","created":"2015-11-26","cited_by_count":514},{"id":"1808.03314","title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network","created":"2018-08-09","cited_by_count":420},{"id":"1911.05485","title":"Diffusion Improves Graph Learning","created":"2019-10-28","cited_by_count":414},{"id":"1905.05583","title":"How to Fine-Tune BERT for Text Classification?","created":"2019-05-14","cited_by_count":411},{"id":"1809.05679","title":"Graph Convolutional Networks for Text Classification","created":"2018-09-15","cited_by_count":345},{"id":"2307.03393","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","created":"2023-07-07","cited_by_count":274},{"id":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"1904.08067","title":"Text Classification Algorithms: A Survey","created":"2019-04-17","cited_by_count":163},{"id":"1605.05101","title":"Recurrent Neural Network for Text Classification with Multi-Task Learning","created":"2016-05-17","cited_by_count":144},{"id":"2004.03705","title":"Deep Learning Based Text Classification: A Comprehensive Review","created":"2020-04-06","cited_by_count":141},{"id":"2202.08235","title":"Data Augmentation for Deep Graph Learning: A Survey","created":"2022-02-16","cited_by_count":133},{"id":"1905.08941","title":"Augmenting Data with Mixup for Sentence Classification: An Empirical Study","created":"2019-05-22","cited_by_count":125},{"id":"2104.14690","title":"Entailment as Few-Shot Learner","created":"2021-04-29","cited_by_count":123},{"id":"2108.13161","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","created":"2021-08-30","cited_by_count":115},{"id":"2004.13826","title":"Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks","created":"2020-04-22","cited_by_count":77},{"id":"2105.05727","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","created":"2021-05-12","cited_by_count":74},{"id":"1805.04174","title":"Joint Embedding of Words and Labels for Text Classification","created":"2018-05-10","cited_by_count":69},{"id":"1904.08398","title":"DocBERT: BERT for Document Classification","created":"2019-04-17","cited_by_count":68},{"id":"2101.03305","title":"LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification","created":"2021-01-09","cited_by_count":61},{"id":"1910.02356","title":"Text Level Graph Neural Network for Text Classification","created":"2019-10-06","cited_by_count":60},{"id":"2001.05313","title":"Tensor Graph Convolutional Networks for Text Classification","created":"2020-01-12","cited_by_count":49},{"id":"2109.03171","title":"Aspect-Controllable Opinion Summarization","created":"2021-09-07","cited_by_count":47},{"id":"1611.06639","title":"Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling","created":"2016-11-21","cited_by_count":39},{"id":"2004.05707","title":"VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification","created":"2020-04-12","cited_by_count":35},{"id":"1901.10444","title":"No Training Required: Exploring Random Encoders for Sentence Classification","created":"2019-01-29","cited_by_count":32},{"id":"2004.12331","title":"Neural Topic Modeling with Bidirectional Adversarial Training","created":"2020-04-26","cited_by_count":29},{"id":"1906.04881","title":"Multiple instance learning with graph neural networks","created":"2019-06-12","cited_by_count":25},{"id":"2105.07107","title":"An Effective Baseline for Robustness to Distributional Shift","created":"2021-05-15","cited_by_count":25},{"id":"1711.09645","title":"Multiple Instance Learning Networks for Fine-Grained Sentiment Analysis","created":"2017-11-27","cited_by_count":23},{"id":"2008.12842","title":"HeteGCN: Heterogeneous Graph Convolutional Networks for Text Classification","created":"2020-08-19","cited_by_count":21},{"id":"1806.04511","title":"Multilingual Sentiment Analysis: An RNN-Based Framework for Limited Data","created":"2018-06-08","cited_by_count":19},{"id":"2102.09604","title":"Privacy-Preserving Graph Convolutional Networks for Text Classification","created":"2021-02-10","cited_by_count":19},{"id":"2112.08652","title":"Extreme Zero-Shot Learning for Extreme Text Classification","created":"2021-12-16","cited_by_count":15},{"id":"2206.00265","title":"InducT-GCN: Inductive Graph Convolutional Networks for Text Classification","created":"2022-06-01","cited_by_count":15},{"id":"2003.11644","title":"Multi-Label Text Classification using Attention-based Graph Neural Network","created":"2020-03-22","cited_by_count":14},{"id":"1810.00664","title":"Text Similarity in Vector Space Models: A Comparative Study","created":"2018-09-24","cited_by_count":13},{"id":"2105.11246","title":"Cross-lingual Text Classification with Heterogeneous Graph Neural Network","created":"2021-05-24","cited_by_count":12},{"id":"2204.04618","title":"ME-GCN: Multi-dimensional Edge-Embedded Graph Convolutional Networks for Semi-supervised Text Classification","created":"2022-04-10","cited_by_count":10},{"id":"2402.08859","title":"Large Language Model with Graph Convolution for Recommendation","created":"2024-02-14","cited_by_count":10},{"id":"2101.04997","title":"Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification","created":"2021-01-13","cited_by_count":8},{"id":"2010.12157","title":"BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks","created":"2020-10-23","cited_by_count":7},{"id":"2203.16060","title":"Understanding Graph Convolutional Networks for Text Classification","created":"2022-03-30","cited_by_count":4},{"id":"2304.04152","title":"Continual Graph Convolutional Network for Text Classification","created":"2023-04-09","cited_by_count":4},{"id":"2403.17216","title":"Ontology Completion with Natural Language Inference and Concept Embeddings: An Analysis","created":"2024-03-25","cited_by_count":4},{"id":"2205.01204","title":"Multi-Task Text Classification using Graph Convolutional Networks for Large-Scale Low Resource Language","created":"2022-05-02","cited_by_count":3}],"next_cursor":null}