{"list":"other","total":55,"rows":[{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2011.00362","title":"A Survey on Contrastive Self-supervised Learning","created":"2020-10-31","cited_by_count":554},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"2006.03659","title":"DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations","created":"2020-06-05","cited_by_count":251},{"id":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2105.11741","title":"ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer","created":"2021-05-25","cited_by_count":231},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"2002.12804","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training","created":"2020-02-28","cited_by_count":204},{"id":"1803.02893","title":"An efficient framework for learning sentence representations","created":"2018-03-07","cited_by_count":198},{"id":"2104.07650","title":"KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction","created":"2021-04-15","cited_by_count":180},{"id":"2106.01760","title":"Template-Based Named Entity Recognition Using BART","created":"2021-06-03","cited_by_count":153},{"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":"2106.07345","title":"Self-Guided Contrastive Learning for BERT Sentence Representations","created":"2021-06-03","cited_by_count":103},{"id":"2103.11955","title":"Improving and Simplifying Pattern Exploiting Training","created":"2021-03-22","cited_by_count":97},{"id":"2109.13532","title":"Template-free Prompt Tuning for Few-shot NER","created":"2021-09-28","cited_by_count":73},{"id":"2201.11147","title":"OntoProtein: Protein Pretraining With Gene Ontology Embedding","created":"2022-01-23","cited_by_count":70},{"id":"2108.10604","title":"Prompt-Learning for Fine-Grained Entity Typing","created":"2021-08-24","cited_by_count":62},{"id":"2202.02113","title":"From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer","created":"2022-02-04","cited_by_count":45},{"id":"2110.08454","title":"Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER","created":"2021-10-16","cited_by_count":38},{"id":"2110.06609","title":"MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators","created":"2021-10-13","cited_by_count":35},{"id":"2201.11332","title":"Ontology-enhanced Prompt-tuning for Few-shot Learning","created":"2022-01-27","cited_by_count":24},{"id":"2109.08306","title":"SentiPrompt: Sentiment Knowledge Enhanced Prompt-Tuning for Aspect-Based Sentiment Analysis","created":"2021-09-17","cited_by_count":23},{"id":"2201.05575","title":"Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings","created":"2022-01-14","cited_by_count":12},{"id":"2110.00479","title":"Learning to Ask for Data-Efficient Event Argument Extraction","created":"2021-10-01","cited_by_count":5},{"id":"2104.04907","title":"Disentangled Contrastive Learning for Learning Robust Textual Representations","created":"2021-04-11","cited_by_count":2},{"id":"2110.07331","title":"Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models","created":"2021-10-14","cited_by_count":1}],"next_cursor":null}