{"list":"other","total":57,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"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":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"1710.03957","title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","created":"2017-10-11","cited_by_count":652},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"2004.13637","title":"Recipes for building an open-domain chatbot","created":"2020-04-28","cited_by_count":593},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"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":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"id":"1603.08023","title":"How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation","created":"2016-03-25","cited_by_count":356},{"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":"2005.00456","title":"USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation","created":"2020-05-01","cited_by_count":188},{"id":"1902.00098","title":"The Second Conversational Intelligence Challenge (ConvAI2)","created":"2019-01-31","cited_by_count":179},{"id":"2006.12719","title":"Unsupervised Evaluation of Interactive Dialog with DialoGPT","created":"2020-06-23","cited_by_count":139},{"id":"1811.00671","title":"Dialogue Natural Language Inference","created":"2018-11-01","cited_by_count":135},{"id":"2005.05339","title":"Enabling Language Models to Fill in the Blanks","created":"2020-05-11","cited_by_count":122},{"id":"1511.06114","title":"Multi-task Sequence to Sequence Learning","created":"2015-11-19","cited_by_count":94},{"id":"2106.03706","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","created":"2021-06-07","cited_by_count":90},{"id":"2010.03994","title":"GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems","created":"2020-10-08","cited_by_count":76},{"id":"2012.13391","title":"I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling","created":"2020-12-24","cited_by_count":68},{"id":"2201.04723","title":"Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents","created":"2022-01-12","cited_by_count":62},{"id":"2009.11321","title":"Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining","created":"2020-09-23","cited_by_count":59},{"id":"2106.01112","title":"DynaEval: Unifying Turn and Dialogue Level Evaluation","created":"2021-06-02","cited_by_count":59},{"id":"1904.03371","title":"Evaluating Coherence in Dialogue Systems using Entailment","created":"2019-04-06","cited_by_count":53},{"id":"1904.10635","title":"Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings","created":"2019-04-24","cited_by_count":52},{"id":"2005.00583","title":"Learning an Unreferenced Metric for Online Dialogue Evaluation","created":"2020-05-01","cited_by_count":52},{"id":"2011.06486","title":"Overview of the Ninth Dialog System Technology Challenge: DSTC9","created":"2020-11-12","cited_by_count":49},{"id":"1907.10568","title":"Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References","created":"2019-07-24","cited_by_count":48},{"id":"2011.00483","title":"Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems","created":"2020-11-01","cited_by_count":47},{"id":"2010.02523","title":"Multi-task Learning for Multilingual Neural Machine Translation","created":"2020-10-06","cited_by_count":46},{"id":"1911.03768","title":"The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents","created":"2019-11-09","cited_by_count":45},{"id":"1906.09308","title":"Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems","created":"2019-06-21","cited_by_count":42},{"id":"2004.04908","title":"Designing Precise and Robust Dialogue Response Evaluators","created":"2020-04-10","cited_by_count":37},{"id":"1911.01456","title":"Predictive Engagement: An Efficient Metric For Automatic Evaluation of Open-Domain Dialogue Systems","created":"2019-11-04","cited_by_count":36},{"id":"2111.02110","title":"Automatic Evaluation and Moderation of Open-domain Dialogue Systems","created":"2021-11-03","cited_by_count":28},{"id":"1908.05859","title":"Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots","created":"2019-08-16","cited_by_count":23},{"id":"2106.05894","title":"Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation","created":"2021-06-10","cited_by_count":16},{"id":"1811.05408","title":"Multi-task learning for Joint Language Understanding and Dialogue State Tracking","created":"2018-11-13","cited_by_count":15},{"id":"2109.13880","title":"Single-dataset Experts for Multi-dataset Question Answering","created":"2021-09-28","cited_by_count":15},{"id":"1901.01824","title":"Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots","created":"2019-01-07","cited_by_count":14},{"id":"2112.07194","title":"MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation","created":"2021-12-14","cited_by_count":13},{"id":"2210.13832","title":"FineD-Eval: Fine-grained Automatic Dialogue-Level Evaluation","created":"2022-10-25","cited_by_count":13},{"id":"2010.12741","title":"An Evaluation Protocol for Generative Conversational Systems","created":"2020-10-24","cited_by_count":9},{"id":"2110.01895","title":"Investigating the Impact of Pre-trained Language Models on Dialog Evaluation","created":"2021-10-05","cited_by_count":4},{"id":"2202.06633","title":"FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows","created":"2022-02-14","cited_by_count":4},{"id":"2111.08808","title":"User Response and Sentiment Prediction for Automatic Dialogue Evaluation","created":"2021-11-16","cited_by_count":3}],"next_cursor":null}