{"list":"other","total":75,"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":"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","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":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"2203.05794","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","created":"2022-03-11","cited_by_count":801},{"id":"2007.01852","title":"Language-agnostic BERT Sentence Embedding","created":"2020-07-03","cited_by_count":627},{"id":"2004.13637","title":"Recipes for building an open-domain chatbot","created":"2020-04-28","cited_by_count":593},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"1908.08345","title":"Text Summarization with Pretrained Encoders","created":"2019-08-22","cited_by_count":556},{"id":"2004.02349","title":"TAPAS: Weakly Supervised Table Parsing via Pre-training","created":"2020-04-05","cited_by_count":434},{"id":"2004.07180","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","created":"2020-04-15","cited_by_count":430},{"id":"2012.14740","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","created":"2020-12-29","cited_by_count":408},{"id":"2005.08314","title":"TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data","created":"2020-05-17","cited_by_count":398},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"2010.00711","title":"A Survey of the State of Explainable AI for Natural Language Processing","created":"2020-10-01","cited_by_count":206},{"id":"2108.02035","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","created":"2021-08-04","cited_by_count":183},{"id":"2010.05171","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","created":"2020-10-11","cited_by_count":176},{"id":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148},{"id":"2211.13308","title":"SciRepEval: A Multi-Format Benchmark for Scientific Document Representations","created":"2022-11-23","cited_by_count":129},{"id":"2005.10433","title":"Text-to-Text Pre-Training for Data-to-Text Tasks","created":"2020-05-21","cited_by_count":104},{"id":"1909.01187","title":"Encode, Tag, Realize: High-Precision Text Editing","created":"2019-09-03","cited_by_count":99},{"id":"2012.04281","title":"CTRLsum: Towards Generic Controllable Text Summarization","created":"2020-12-08","cited_by_count":98},{"id":"2110.08527","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","created":"2021-10-16","cited_by_count":97},{"id":"2012.00893","title":"Evaluating Explanations: How much do explanations from the teacher aid students?","created":"2020-12-01","cited_by_count":94},{"id":"2001.09694","title":"Retrospective Reader for Machine Reading Comprehension","created":"2020-01-27","cited_by_count":86},{"id":"2202.06671","title":"Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings","created":"2022-02-14","cited_by_count":75},{"id":"1805.07043","title":"Aspect Based Sentiment Analysis with Gated Convolutional Networks","created":"2018-05-18","cited_by_count":65},{"id":"2104.00235","title":"Multilingual and code-switching ASR challenges for low resource Indian languages","created":"2021-04-01","cited_by_count":53},{"id":"1907.02684","title":"Head-Driven Phrase Structure Grammar Parsing on Penn Treebank","created":"2019-07-05","cited_by_count":43},{"id":"2210.00105","title":"A Decade of Knowledge Graphs in Natural Language Processing: A Survey","created":"2022-09-30","cited_by_count":40},{"id":"1805.12216","title":"A Web-scale system for scientific knowledge exploration","created":"2018-05-30","cited_by_count":39},{"id":"2211.16285","title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","created":"2022-11-29","cited_by_count":39},{"id":"2008.06788","title":"Is Supervised Syntactic Parsing Beneficial for Language Understanding? An Empirical Investigation","created":"2020-08-15","cited_by_count":34},{"id":"2104.05837","title":"Relational World Knowledge Representation in Contextual Language Models: A Review","created":"2021-04-12","cited_by_count":31},{"id":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30},{"id":"2003.13016","title":"A Dataset of German Legal Documents for Named Entity Recognition","created":"2020-03-29","cited_by_count":24},{"id":"2005.00912","title":"Examining Citations of Natural Language Processing Literature","created":"2020-05-02","cited_by_count":20},{"id":"2108.05682","title":"(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models' Performance","created":"2021-08-12","cited_by_count":20},{"id":"2210.05245","title":"PatternRank: Leveraging Pretrained Language Models and Part of Speech for Unsupervised Keyphrase Extraction","created":"2022-10-11","cited_by_count":19},{"id":"2210.14424","title":"Geographic Citation Gaps in NLP Research","created":"2022-10-26","cited_by_count":19},{"id":"2204.04163","title":"Contextual Representation Learning beyond Masked Language Modeling","created":"2022-04-08","cited_by_count":16},{"id":"2010.12885","title":"Unsupervised Paraphrasing with Pretrained Language Models","created":"2020-10-24","cited_by_count":15},{"id":"1703.10090","title":"A Short Review of Ethical Challenges in Clinical Natural Language Processing","created":"2017-03-29","cited_by_count":14},{"id":"2109.08207","title":"Numerical reasoning in machine reading comprehension tasks: are we there yet?","created":"2021-09-16","cited_by_count":9},{"id":"1910.07351","title":"NLPExplorer: Exploring the Universe of NLP Papers","created":"2019-10-16","cited_by_count":8},{"id":"2006.01131","title":"NLP Scholar: An Interactive Visual Explorer for Natural Language Processing Literature","created":"2020-05-31","cited_by_count":8},{"id":"2210.06023","title":"Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined Topics","created":"2022-10-12","cited_by_count":7},{"id":"2307.03104","title":"Efficient Domain Adaptation of Sentence Embeddings Using Adapters","created":"2023-07-06","cited_by_count":6},{"id":"2205.05128","title":"Human Language Modeling","created":"2022-05-10","cited_by_count":5},{"id":"2307.07851","title":"AspectCSE: Sentence Embeddings for Aspect-based Semantic Textual Similarity Using Contrastive Learning and Structured Knowledge","created":"2023-07-15","cited_by_count":5}],"next_cursor":null}