{"list":"other","total":72,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"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":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"1801.10112","title":"Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence","created":"2018-01-30","cited_by_count":742},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"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":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"1909.05855","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","created":"2019-09-12","cited_by_count":434},{"id":"2003.04807","title":"Efficient Intent Detection with Dual Sentence Encoders","created":"2020-03-10","cited_by_count":433},{"id":"1909.02027","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","created":"2019-09-04","cited_by_count":386},{"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":"1611.06194","title":"Expert Gate: Lifelong Learning with a Network of Experts","created":"2016-11-18","cited_by_count":372},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"1811.08051","title":"Learning without Memorizing","created":"2018-11-20","cited_by_count":250},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"1703.10960","title":"Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders","created":"2017-03-31","cited_by_count":222},{"id":"1903.10145","title":"Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing","created":"2019-03-25","cited_by_count":191},{"id":"1711.10563","title":"FearNet: Brain-Inspired Model for Incremental Learning","created":"2017-11-28","cited_by_count":177},{"id":"1903.05566","title":"Benchmarking Natural Language Understanding Services for building Conversational Agents","created":"2019-03-13","cited_by_count":166},{"id":"1909.03329","title":"LAMOL: LAnguage MOdeling for Lifelong Language Learning","created":"2019-09-07","cited_by_count":160},{"id":"2004.04092","title":"Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space","created":"2020-04-05","cited_by_count":114},{"id":"2110.07298","title":"LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5","created":"2021-10-14","cited_by_count":104},{"id":"1704.01920","title":"Encoder Based Lifelong Learning","created":"2017-04-06","cited_by_count":102},{"id":"1906.02425","title":"Uncertainty-guided Continual Learning with Bayesian Neural Networks","created":"2019-06-06","cited_by_count":102},{"id":"2111.14592","title":"GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection","created":"2021-11-29","cited_by_count":102},{"id":"1810.07942","title":"Semantic Parsing for Task Oriented Dialog using Hierarchical Representations","created":"2018-10-18","cited_by_count":101},{"id":"2112.02706","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","created":"2021-12-05","cited_by_count":91},{"id":"2009.01797","title":"A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning","created":"2020-09-03","cited_by_count":87},{"id":"2012.15504","title":"Continual Learning in Task-Oriented Dialogue Systems","created":"2020-12-31","cited_by_count":83},{"id":"2003.07490","title":"Recent Advances and Challenges in Task-oriented Dialog System","created":"2020-03-17","cited_by_count":78},{"id":"2008.03946","title":"A Large-Scale Chinese Short-Text Conversation Dataset","created":"2020-08-10","cited_by_count":77},{"id":"1911.04700","title":"A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data","created":"2019-11-12","cited_by_count":74},{"id":"2010.00910","title":"Continual Learning for Natural Language Generation in Task-oriented Dialog Systems","created":"2020-10-02","cited_by_count":47},{"id":"2101.00828","title":"Transformer-based Conditional Variational Autoencoder for Controllable Story Generation","created":"2021-01-04","cited_by_count":44},{"id":"2203.06654","title":"Continual Prompt Tuning for Dialog State Tracking","created":"2022-03-13","cited_by_count":44},{"id":"2005.08866","title":"Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations","created":"2020-05-18","cited_by_count":42},{"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":"2106.00291","title":"Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking","created":"2021-06-01","cited_by_count":35},{"id":"2108.01547","title":"EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training","created":"2021-08-03","cited_by_count":34},{"id":"2209.06664","title":"SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation","created":"2022-09-14","cited_by_count":34},{"id":"2010.02123","title":"Lifelong Language Knowledge Distillation","created":"2020-10-05","cited_by_count":31},{"id":"2108.07154","title":"MMChat: Multi-Modal Chat Dataset on Social Media","created":"2021-08-16","cited_by_count":30},{"id":"2209.06638","title":"SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding","created":"2022-09-14","cited_by_count":28},{"id":"2105.14556","title":"Diversifying Dialog Generation via Adaptive Label Smoothing","created":"2021-05-30","cited_by_count":25},{"id":"2107.08173","title":"Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking","created":"2021-07-17","cited_by_count":22},{"id":"2009.09427","title":"Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Data","created":"2020-09-20","cited_by_count":20},{"id":"2009.12719","title":"Stylized Dialogue Response Generation Using Stylized Unpaired Texts","created":"2020-09-27","cited_by_count":16},{"id":"2104.11939","title":"Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation","created":"2021-04-24","cited_by_count":14},{"id":"2111.00667","title":"Unsupervised Domain Adaptation with Adapter","created":"2021-11-01","cited_by_count":14},{"id":"2203.11670","title":"Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation","created":"2022-03-22","cited_by_count":8},{"id":"2106.03065","title":"Semantic-Enhanced Explainable Finetuning for Open-Domain Dialogues","created":"2021-06-06","cited_by_count":3}],"next_cursor":null}