{"list":"other","total":73,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"1811.05868","title":"Pitfalls of Graph Neural Network Evaluation","created":"2018-11-14","cited_by_count":1007},{"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":"2005.00547","title":"GoEmotions: A Dataset of Fine-Grained Emotions","created":"2020-05-01","cited_by_count":486},{"id":"1809.05679","title":"Graph Convolutional Networks for Text Classification","created":"2018-09-15","cited_by_count":345},{"id":"1909.00161","title":"Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach","created":"2019-08-31","cited_by_count":308},{"id":"1907.12412","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","created":"2019-07-29","cited_by_count":231},{"id":"1907.06902","title":"Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches","created":"2019-07-16","cited_by_count":185},{"id":"1404.2188","title":"A Convolutional Neural Network for Modelling Sentences","created":"2014-04-08","cited_by_count":163},{"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":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111},{"id":"1709.08267","title":"HDLTex: Hierarchical Deep Learning for Text Classification","created":"2017-09-24","cited_by_count":106},{"id":"2011.11197","title":"The Emerging Trends of Multi-Label Learning","created":"2020-11-23","cited_by_count":100},{"id":"1508.00200","title":"PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks","created":"2015-08-02","cited_by_count":96},{"id":"1510.03820","title":"A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification","created":"2015-10-13","cited_by_count":92},{"id":"2106.05609","title":"GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings","created":"2021-06-10","cited_by_count":90},{"id":"1806.04822","title":"SGM: Sequence Generation Model for Multi-label Classification","created":"2018-06-13","cited_by_count":89},{"id":"2008.00364","title":"A Survey on Text Classification: From Shallow to Deep Learning","created":"2020-08-02","cited_by_count":80},{"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":"2011.00387","title":"Be More with Less: Hypergraph Attention Networks for Inductive Text Classification","created":"2020-11-01","cited_by_count":74},{"id":"2105.05727","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","created":"2021-05-12","cited_by_count":74},{"id":"2110.00685","title":"Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification","created":"2021-10-01","cited_by_count":67},{"id":"1910.02356","title":"Text Level Graph Neural Network for Text Classification","created":"2019-10-06","cited_by_count":60},{"id":"1805.09843","title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","created":"2018-05-24","cited_by_count":53},{"id":"2203.03825","title":"Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification","created":"2022-03-08","cited_by_count":52},{"id":"2001.05313","title":"Tensor Graph Convolutional Networks for Text Classification","created":"2020-01-12","cited_by_count":49},{"id":"2005.13012","title":"Comparing BERT against traditional machine learning text classification","created":"2020-05-26","cited_by_count":46},{"id":"2010.01653","title":"An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels","created":"2020-10-04","cited_by_count":44},{"id":"1906.02242","title":"Variational Pretraining for Semi-supervised Text Classification","created":"2019-06-05","cited_by_count":41},{"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":"2010.15728","title":"Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisation","created":"2020-10-29","cited_by_count":38},{"id":"2109.04712","title":"Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution","created":"2021-09-10","cited_by_count":35},{"id":"1906.04898","title":"Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification","created":"2019-06-09","cited_by_count":32},{"id":"2002.03067","title":"Description Based Text Classification with Reinforcement Learning","created":"2020-02-08","cited_by_count":27},{"id":"2109.07437","title":"Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative","created":"2021-09-15","cited_by_count":26},{"id":"2110.02591","title":"Weakly-supervised Text Classification Based on Keyword Graph","created":"2021-10-06","cited_by_count":25},{"id":"2008.12842","title":"HeteGCN: Heterogeneous Graph Convolutional Networks for Text Classification","created":"2020-08-19","cited_by_count":21},{"id":"2109.03777","title":"Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP","created":"2021-09-08","cited_by_count":17},{"id":"2112.06386","title":"Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification","created":"2021-12-13","cited_by_count":15},{"id":"2111.00180","title":"Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification","created":"2021-10-30","cited_by_count":13},{"id":"2204.00811","title":"Constrained Sequence-to-Tree Generation for Hierarchical Text Classification","created":"2022-04-02","cited_by_count":13},{"id":"2009.10938","title":"LA-HCN: Label-based Attention for Hierarchical Multi-label TextClassification Neural Network","created":"2020-09-23","cited_by_count":11},{"id":"2202.11345","title":"Prompt-Learning for Short Text Classification","created":"2022-02-23","cited_by_count":11},{"id":"1801.06717","title":"Using Deep Learning for Title-Based Semantic Subject Indexing to Reach Competitive Performance to Full-Text","created":"2018-01-20","cited_by_count":10},{"id":"2104.01666","title":"Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning","created":"2021-04-04","cited_by_count":9},{"id":"2109.07319","title":"InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme Classification","created":"2021-09-13","cited_by_count":8},{"id":"1902.09347","title":"Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification","created":"2019-02-25","cited_by_count":5},{"id":"1705.05311","title":"Using Titles vs. Full-text as Source for Automated Semantic Document Annotation","created":"2017-05-15","cited_by_count":4},{"id":"1903.12090","title":"Learning to Weight for Text Classification","created":"2019-03-28","cited_by_count":4},{"id":"2006.15795","title":"Combine Convolution with Recurrent Networks for Text Classification","created":"2020-06-29","cited_by_count":2}],"next_cursor":null}