{"list":"other","total":62,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"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":"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":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"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":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"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":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"1812.10464","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","created":"2018-12-26","cited_by_count":434},{"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":"1911.03894","title":"CamemBERT: a Tasty French Language Model","created":"2019-11-10","cited_by_count":368},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2005.00796","title":"A Simple Language Model for Task-Oriented Dialogue","created":"2020-05-02","cited_by_count":332},{"id":"2010.15980","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","created":"2020-10-29","cited_by_count":249},{"id":"2008.09335","title":"MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark","created":"2020-08-21","cited_by_count":158},{"id":"1912.05372","title":"FlauBERT: Unsupervised Language Model Pre-training for French","created":"2019-12-11","cited_by_count":153},{"id":"2003.00744","title":"PhoBERT: Pre-trained language models for Vietnamese","created":"2020-03-02","cited_by_count":149},{"id":"1905.12688","title":"Choosing Transfer Languages for Cross-Lingual Learning","created":"2019-05-29","cited_by_count":144},{"id":"1810.13327","title":"Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialog","created":"2018-10-31","cited_by_count":125},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114},{"id":"2009.05387","title":"IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding","created":"2020-09-11","cited_by_count":109},{"id":"1909.02188","title":"A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding","created":"2019-09-05","cited_by_count":107},{"id":"2010.08824","title":"Knowledge-Grounded Dialogue Generation with Pre-trained Language Models","created":"2020-10-17","cited_by_count":107},{"id":"2009.12005","title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","created":"2020-09-25","cited_by_count":103},{"id":"2105.00572","title":"Larger-Scale Transformers for Multilingual Masked Language Modeling","created":"2021-05-02","cited_by_count":87},{"id":"2004.14353","title":"End-to-End Slot Alignment and Recognition for Cross-Lingual NLU","created":"2020-04-29","cited_by_count":83},{"id":"2105.04222","title":"Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking","created":"2021-05-10","cited_by_count":61},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57},{"id":"2103.13309","title":"Are Multilingual Models Effective in Code-Switching?","created":"2021-03-24","cited_by_count":56},{"id":"2106.02787","title":"BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling","created":"2021-06-05","cited_by_count":56},{"id":"1909.08582","title":"Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences","created":"2019-09-18","cited_by_count":55},{"id":"1911.09273","title":"Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems","created":"2019-11-21","cited_by_count":42},{"id":"2008.06239","title":"Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems","created":"2020-08-14","cited_by_count":41},{"id":"2106.08226","title":"Consistency Regularization for Cross-Lingual Fine-Tuning","created":"2021-06-15","cited_by_count":41},{"id":"2010.12321","title":"BARThez: a Skilled Pretrained French Sequence-to-Sequence Model","created":"2020-10-23","cited_by_count":40},{"id":"2003.07568","title":"XPersona: Evaluating Multilingual Personalized Chatbot","created":"2020-03-17","cited_by_count":36},{"id":"2009.13656","title":"Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems","created":"2020-09-28","cited_by_count":35},{"id":"2012.01687","title":"Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition","created":"2020-12-03","cited_by_count":35},{"id":"2104.08757","title":"Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders","created":"2021-04-18","cited_by_count":24},{"id":"1911.04081","title":"Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables","created":"2019-11-11","cited_by_count":21},{"id":"2004.09571","title":"Language-agnostic Multilingual Modeling","created":"2020-04-20","cited_by_count":17},{"id":"2008.03979","title":"KR-BERT: A Small-Scale Korean-Specific Language Model","created":"2020-08-10","cited_by_count":17},{"id":"2010.13912","title":"Probing Task-Oriented Dialogue Representation from Language Models","created":"2020-10-26","cited_by_count":15},{"id":"1809.04163","title":"Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization","created":"2018-09-11","cited_by_count":12},{"id":"2109.06762","title":"Greenformer: Factorization Toolkit for Efficient Deep Neural Networks","created":"2021-09-14","cited_by_count":7},{"id":"2104.06268","title":"Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling","created":"2021-04-13","cited_by_count":4},{"id":"2106.03777","title":"X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing","created":"2021-06-07","cited_by_count":4}],"next_cursor":null}