{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1606.07947","title":"Sequence-Level Knowledge Distillation","created":"2016-06-25","cited_by_count":801},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1908.05739","title":"Abductive Commonsense Reasoning","created":"2019-08-15","cited_by_count":301},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251},{"id":"2012.15828","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","created":"2020-12-31","cited_by_count":245},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"2011.00416","title":"Deep Learning for Text Style Transfer: A Survey","created":"2020-11-01","cited_by_count":162},{"id":"2112.05682","title":"Self-attention Does Not Need $O(n^2)$ Memory","created":"2021-12-10","cited_by_count":154},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150},{"id":"1711.06861","title":"Style Transfer in Text: Exploration and Evaluation","created":"2017-11-18","cited_by_count":146},{"id":"2004.02990","title":"Evaluating the Evaluation of Diversity in Natural Language Generation","created":"2020-04-06","cited_by_count":129},{"id":"2005.03642","title":"On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation","created":"2020-05-07","cited_by_count":127},{"id":"1910.00292","title":"Generalization in Generation: A closer look at Exposure Bias","created":"2019-10-01","cited_by_count":123},{"id":"2204.01171","title":"Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation","created":"2022-04-03","cited_by_count":108},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78},{"id":"2010.13002","title":"Pre-trained Summarization Distillation","created":"2020-10-24","cited_by_count":71},{"id":"2008.05221","title":"Compression of Deep Learning Models for Text: A Survey","created":"2020-08-12","cited_by_count":64},{"id":"1707.01161","title":"Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models","created":"2017-07-04","cited_by_count":57},{"id":"2004.05686","title":"XtremeDistil: Multi-stage Distillation for Massive Multilingual Models","created":"2020-04-12","cited_by_count":38},{"id":"2202.12350","title":"DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation","created":"2022-02-24","cited_by_count":37},{"id":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36},{"id":"2009.07032","title":"Noisy Self-Knowledge Distillation for Text Summarization","created":"2020-09-15","cited_by_count":31},{"id":"2203.11239","title":"DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization","created":"2022-03-21","cited_by_count":23},{"id":"2109.08705","title":"Relating Neural Text Degeneration to Exposure Bias","created":"2021-09-17","cited_by_count":19},{"id":"2011.13477","title":"Decoding and Diversity in Machine Translation","created":"2020-11-26","cited_by_count":15},{"id":"2106.03441","title":"Attention Temperature Matters in Abstractive Summarization Distillation","created":"2021-06-07","cited_by_count":14},{"id":"2108.12963","title":"Scheduled Sampling Based on Decoding Steps for Neural Machine Translation","created":"2021-08-30","cited_by_count":11},{"id":"2101.07086","title":"Model Compression for Domain Adaptation through Causal Effect Estimation","created":"2021-01-18","cited_by_count":6},{"id":"1904.04079","title":"Differentiable Sampling with Flexible Reference Word Order for Neural Machine Translation","created":"2019-04-04","cited_by_count":5},{"id":"2109.04114","title":"Fixing exposure bias with imitation learning needs powerful oracles","created":"2021-09-09","cited_by_count":3}],"next_cursor":null}