{"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":"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":"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":"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":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1912.08777","title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","created":"2019-12-18","cited_by_count":1102},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"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":"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":"1805.10190","title":"Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces","created":"2018-05-25","cited_by_count":377},{"id":"2005.00796","title":"A Simple Language Model for Task-Oriented Dialogue","created":"2020-05-02","cited_by_count":332},{"id":"1906.03158","title":"Matching the Blanks: Distributional Similarity for Relation Learning","created":"2019-06-07","cited_by_count":272},{"id":"1909.03546","title":"Entity, Relation, and Event Extraction with Contextualized Span Representations","created":"2019-09-08","cited_by_count":262},{"id":"1810.10147","title":"FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation","created":"2018-10-24","cited_by_count":254},{"id":"1905.08743","title":"Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems","created":"2019-05-21","cited_by_count":216},{"id":"2007.12720","title":"MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines","created":"2020-07-10","cited_by_count":204},{"id":"1910.11476","title":"A Unified MRC Framework for Named Entity Recognition","created":"2019-10-25","cited_by_count":199},{"id":"2101.05779","title":"Structured Prediction as Translation between Augmented Natural Languages","created":"2021-01-14","cited_by_count":183},{"id":"1911.02855","title":"Dice Loss for Data-imbalanced NLP Tasks","created":"2019-11-07","cited_by_count":182},{"id":"2005.04611","title":"How Context Affects Language Models' Factual Predictions","created":"2020-05-10","cited_by_count":181},{"id":"1904.05255","title":"Simple BERT Models for Relation Extraction and Semantic Role Labeling","created":"2019-04-10","cited_by_count":154},{"id":"2005.07150","title":"Named Entity Recognition as Dependency Parsing","created":"2020-05-14","cited_by_count":151},{"id":"1804.05392","title":"Higher-order Coreference Resolution with Coarse-to-fine Inference","created":"2018-04-15","cited_by_count":150},{"id":"2106.01223","title":"A Unified Generative Framework for Various NER Subtasks","created":"2021-06-02","cited_by_count":141},{"id":"2106.13353","title":"Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models","created":"2021-06-24","cited_by_count":139},{"id":"1909.07755","title":"Span-based Joint Entity and Relation Extraction with Transformer Pre-training","created":"2019-09-17","cited_by_count":133},{"id":"1908.09091","title":"BERT for Coreference Resolution: Baselines and Analysis","created":"2019-08-24","cited_by_count":125},{"id":"2106.09231","title":"Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases","created":"2021-06-17","cited_by_count":107},{"id":"2010.11967","title":"Language Models are Open Knowledge Graphs","created":"2020-10-22","cited_by_count":95},{"id":"1910.07124","title":"FewRel 2.0: Towards More Challenging Few-Shot Relation Classification","created":"2019-10-16","cited_by_count":94},{"id":"1904.03296","title":"A General Framework for Information Extraction using Dynamic Span Graphs","created":"2019-04-05","cited_by_count":93},{"id":"1911.01746","title":"Coreference Resolution as Query-based Span Prediction","created":"2019-11-05","cited_by_count":91},{"id":"1907.00390","title":"A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling","created":"2019-06-30","cited_by_count":85},{"id":"2109.03659","title":"Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction","created":"2021-09-08","cited_by_count":73},{"id":"2002.03079","title":"Blank Language Models","created":"2020-02-08","cited_by_count":43},{"id":"1903.07785","title":"Cloze-driven Pretraining of Self-attention Networks","created":"2019-03-19","cited_by_count":41},{"id":"1909.04273","title":"Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategy","created":"2019-09-10","cited_by_count":41},{"id":"1812.00195","title":"One for All: Neural Joint Modeling of Entities and Events","created":"2018-12-01","cited_by_count":37},{"id":"1901.00158","title":"Text Infilling","created":"2019-01-01","cited_by_count":32},{"id":"1807.06517","title":"Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing","created":"2018-07-17","cited_by_count":29},{"id":"2009.13272","title":"Augmented Natural Language for Generative Sequence Labeling","created":"2020-09-15","cited_by_count":29},{"id":"2002.07972","title":"The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding","created":"2020-02-19","cited_by_count":28},{"id":"1901.05280","title":"Dependency or Span, End-to-End Uniform Semantic Role Labeling","created":"2019-01-16","cited_by_count":22},{"id":"2109.11171","title":"Zero-Shot Information Extraction as a Unified Text-to-Triple Translation","created":"2021-09-23","cited_by_count":22},{"id":"1904.12324","title":"OPIEC: An Open Information Extraction Corpus","created":"2019-04-28","cited_by_count":20},{"id":"1603.01648","title":"Getting More Out Of Syntax with PropS","created":"2016-03-04","cited_by_count":8},{"id":"1603.06270","title":"Multi-Task Cross-Lingual Sequence Tagging from Scratch","created":"2016-03-20","cited_by_count":6},{"id":"2004.03636","title":"Efficient long-distance relation extraction with DG-SpanBERT","created":"2020-04-07","cited_by_count":5}],"next_cursor":null}