{"list":"other","total":56,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"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":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"1710.03957","title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","created":"2017-10-11","cited_by_count":652},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"2106.05931","title":"Score-based Generative Modeling in Latent Space","created":"2021-06-10","cited_by_count":636},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"2102.05379","title":"Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions","created":"2021-02-10","cited_by_count":574},{"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":"2011.10650","title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","created":"2020-11-20","cited_by_count":264},{"id":"1709.03815","title":"OpenNMT: Open-source Toolkit for Neural Machine Translation","created":"2017-09-12","cited_by_count":251},{"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":"2001.04063","title":"ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training","created":"2020-01-13","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":"1605.06069","title":"A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues","created":"2016-05-19","cited_by_count":174},{"id":"1910.07931","title":"PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable","created":"2019-10-17","cited_by_count":145},{"id":"2006.12719","title":"Unsupervised Evaluation of Interactive Dialog with DialoGPT","created":"2020-06-23","cited_by_count":139},{"id":"2004.04092","title":"Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space","created":"2020-04-05","cited_by_count":114},{"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":"1905.04982","title":"Learning Hierarchical Priors in VAEs","created":"2019-05-13","cited_by_count":53},{"id":"2210.07626","title":"BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation","created":"2022-10-14","cited_by_count":48},{"id":"2202.07477","title":"Understanding DDPM Latent Codes Through Optimal Transport","created":"2022-02-14","cited_by_count":45},{"id":"1805.12352","title":"DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder","created":"2018-05-31","cited_by_count":44},{"id":"2204.13031","title":"DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation","created":"2022-04-27","cited_by_count":35},{"id":"1804.08069","title":"Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation","created":"2018-04-22","cited_by_count":34},{"id":"1702.02390","title":"A Hybrid Convolutional Variational Autoencoder for Text Generation","created":"2017-02-08","cited_by_count":33},{"id":"1909.00868","title":"A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text","created":"2019-09-02","cited_by_count":32},{"id":"1905.05471","title":"Improving Neural Conversational Models with Entropy-Based Data Filtering","created":"2019-05-14","cited_by_count":30},{"id":"1712.08207","title":"Variational Attention for Sequence-to-Sequence Models","created":"2017-12-21","cited_by_count":29},{"id":"2208.00638","title":"Composable Text Controls in Latent Space with ODEs","created":"2022-08-01","cited_by_count":28},{"id":"1908.11527","title":"Implicit Deep Latent Variable Models for Text Generation","created":"2019-08-30","cited_by_count":26},{"id":"2207.06130","title":"Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation","created":"2022-07-13","cited_by_count":20},{"id":"2106.03410","title":"Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders","created":"2021-06-07","cited_by_count":18},{"id":"1911.09845","title":"A Discrete CVAE for Response Generation on Short-Text Conversation","created":"2019-11-22","cited_by_count":17},{"id":"1705.00316","title":"A Conditional Variational Framework for Dialog Generation","created":"2017-04-30","cited_by_count":16},{"id":"2210.05725","title":"Measuring and Improving Semantic Diversity of Dialogue Generation","created":"2022-10-11","cited_by_count":16},{"id":"1906.01781","title":"Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selection","created":"2019-06-05","cited_by_count":8},{"id":"2212.01145","title":"Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables","created":"2022-12-02","cited_by_count":5},{"id":"2209.12590","title":"Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs","created":"2022-09-26","cited_by_count":3}],"next_cursor":null}