{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"1408.5882","title":"Convolutional Neural Networks for Sentence Classification","created":"2014-08-25","cited_by_count":1127},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"1909.08478","title":"Simple, Scalable Adaptation for Neural Machine Translation","created":"2019-09-18","cited_by_count":242},{"id":"2010.11918","title":"AdapterDrop: On the Efficiency of Adapters in Transformers","created":"2020-10-22","cited_by_count":224},{"id":"2010.00710","title":"Nearest Neighbor Machine Translation","created":"2020-10-01","cited_by_count":209},{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202},{"id":"1804.06437","title":"Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer","created":"2018-04-17","cited_by_count":191},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"2110.07577","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","created":"2021-10-14","cited_by_count":162},{"id":"2004.02105","title":"Unsupervised Domain Clusters in Pretrained Language Models","created":"2020-04-05","cited_by_count":160},{"id":"1909.01380","title":"The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives","created":"2019-09-03","cited_by_count":139},{"id":"1803.05567","title":"Achieving Human Parity on Automatic Chinese to English News Translation","created":"2018-03-15","cited_by_count":119},{"id":"2109.04212","title":"Efficient Nearest Neighbor Language Models","created":"2021-09-09","cited_by_count":93},{"id":"2102.02557","title":"Adaptive Semiparametric Language Models","created":"2021-02-04","cited_by_count":83},{"id":"1810.03581","title":"Improving the Transformer Translation Model with Document-Level Context","created":"2018-10-08","cited_by_count":74},{"id":"1806.00258","title":"A Survey of Domain Adaptation for Neural Machine Translation","created":"2018-06-01","cited_by_count":64},{"id":"2110.06176","title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention","created":"2021-10-12","cited_by_count":43},{"id":"2210.16773","title":"An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks","created":"2022-10-30","cited_by_count":36},{"id":"1906.00376","title":"Domain Adaptation of Neural Machine Translation by Lexicon Induction","created":"2019-06-02","cited_by_count":33},{"id":"2207.11681","title":"Learning Graph Neural Networks for Image Style Transfer","created":"2022-07-24","cited_by_count":29},{"id":"1806.04357","title":"Multi-Task Neural Models for Translating Between Styles Within and Across Languages","created":"2018-06-12","cited_by_count":28},{"id":"1805.01817","title":"Extreme Adaptation for Personalized Neural Machine Translation","created":"2018-05-04","cited_by_count":27},{"id":"1909.09962","title":"Adapting Language Models for Non-Parallel Author-Stylized Rewriting","created":"2019-09-22","cited_by_count":23},{"id":"2012.07162","title":"Mask-Align: Self-Supervised Neural Word Alignment","created":"2020-12-13","cited_by_count":20},{"id":"2109.06604","title":"Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation","created":"2021-09-14","cited_by_count":20},{"id":"2204.04581","title":"Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering","created":"2022-04-10","cited_by_count":19},{"id":"1911.08706","title":"Controlling Neural Machine Translation Formality with Synthetic Supervision","created":"2019-11-20","cited_by_count":18},{"id":"2106.03297","title":"On the Language Coverage Bias for Neural Machine Translation","created":"2021-06-07","cited_by_count":12},{"id":"1908.07195","title":"ARAML: A Stable Adversarial Training Framework for Text Generation","created":"2019-08-20","cited_by_count":9},{"id":"2204.00665","title":"CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation","created":"2022-04-01","cited_by_count":9},{"id":"2206.09337","title":"Learning Multiscale Transformer Models for Sequence Generation","created":"2022-06-19","cited_by_count":7},{"id":"2101.11836","title":"DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting","created":"2021-01-28","cited_by_count":5},{"id":"2102.10243","title":"Machine Translation Customization via Automatic Training Data Selection from the Web","created":"2021-02-20","cited_by_count":2}],"next_cursor":null}