{"list":"other","total":60,"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2003.07082","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","created":"2020-03-16","cited_by_count":723},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"1611.01734","title":"Deep Biaffine Attention for Neural Dependency Parsing","created":"2016-11-06","cited_by_count":334},{"id":"1503.00075","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","created":"2015-02-28","cited_by_count":306},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2010.11918","title":"AdapterDrop: On the Efficiency of Adapters in Transformers","created":"2020-10-22","cited_by_count":224},{"id":"2110.07577","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","created":"2021-10-14","cited_by_count":162},{"id":"1601.00770","title":"End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures","created":"2016-01-05","cited_by_count":161},{"id":"1809.10185","title":"Graph Convolution over Pruned Dependency Trees Improves Relation Extraction","created":"2018-09-26","cited_by_count":146},{"id":"1703.04826","title":"Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling","created":"2017-03-14","cited_by_count":137},{"id":"1909.02209","title":"Semantics-aware BERT for Language Understanding","created":"2019-09-05","cited_by_count":112},{"id":"2004.12362","title":"Relational Graph Attention Network for Aspect-based Sentiment Analysis","created":"2020-04-26","cited_by_count":104},{"id":"1810.09536","title":"Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks","created":"2018-10-22","cited_by_count":101},{"id":"1911.03090","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning","created":"2019-11-08","cited_by_count":89},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82},{"id":"2202.07962","title":"Revisiting Parameter-Efficient Tuning: Are We Really There Yet?","created":"2022-02-16","cited_by_count":76},{"id":"1804.08199","title":"Linguistically-Informed Self-Attention for Semantic Role Labeling","created":"2018-04-23","cited_by_count":71},{"id":"1704.04675","title":"Graph Convolutional Encoders for Syntax-aware Neural Machine Translation","created":"2017-04-15","cited_by_count":70},{"id":"1909.06639","title":"Tree Transformer: Integrating Tree Structures into Self-Attention","created":"2019-09-14","cited_by_count":68},{"id":"2104.10809","title":"Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?","created":"2021-04-22","cited_by_count":55},{"id":"2103.04350","title":"Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees","created":"2021-03-07","cited_by_count":51},{"id":"2008.09084","title":"Do Syntax Trees Help Pre-trained Transformers Extract Information?","created":"2020-08-20","cited_by_count":48},{"id":"2106.14282","title":"A Closer Look at How Fine-tuning Changes BERT","created":"2021-06-27","cited_by_count":42},{"id":"2104.09635","title":"Refining Targeted Syntactic Evaluation of Language Models","created":"2021-04-19","cited_by_count":41},{"id":"1909.02606","title":"Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks","created":"2019-09-05","cited_by_count":40},{"id":"2005.01641","title":"A Tale of a Probe and a Parser","created":"2020-05-04","cited_by_count":40},{"id":"2108.02340","title":"Robust Transfer Learning with Pretrained Language Models through Adapters","created":"2021-08-05","cited_by_count":35},{"id":"2207.06646","title":"DropNet: Reducing Neural Network Complexity via Iterative Pruning","created":"2022-07-14","cited_by_count":29},{"id":"2108.00104","title":"Structural Guidance for Transformer Language Models","created":"2021-07-30","cited_by_count":25},{"id":"1909.00383","title":"Self-Attention with Structural Position Representations","created":"2019-09-01","cited_by_count":21},{"id":"2005.13482","title":"Syntactic Structure Distillation Pretraining For Bidirectional Encoders","created":"2020-05-27","cited_by_count":18},{"id":"2012.05395","title":"Infusing Finetuning with Semantic Dependencies","created":"2020-12-10","cited_by_count":18},{"id":"2005.09099","title":"(Re)construing Meaning in NLP","created":"2020-05-18","cited_by_count":16},{"id":"1605.07515","title":"Neural Semantic Role Labeling with Dependency Path Embeddings","created":"2016-05-24","cited_by_count":15},{"id":"1611.05774","title":"What Do Recurrent Neural Network Grammars Learn About Syntax?","created":"2016-11-17","cited_by_count":15},{"id":"1909.02222","title":"Multi-Granularity Self-Attention for Neural Machine Translation","created":"2019-09-05","cited_by_count":10},{"id":"2112.07874","title":"Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling","created":"2021-12-15","cited_by_count":10},{"id":"2112.05364","title":"Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation","created":"2021-12-10","cited_by_count":6},{"id":"2210.13002","title":"An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding Tasks","created":"2022-10-24","cited_by_count":2}],"next_cursor":null}