{"list":"other","total":90,"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"2003.07082","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","created":"2020-03-16","cited_by_count":723},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"1611.01734","title":"Deep Biaffine Attention for Neural Dependency Parsing","created":"2016-11-06","cited_by_count":334},{"id":"1902.09666","title":"Predicting the Type and Target of Offensive Posts in Social Media","created":"2019-02-25","cited_by_count":271},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"2004.01401","title":"XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation","created":"2020-04-03","cited_by_count":222},{"id":"1605.09096","title":"Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change","created":"2016-05-30","cited_by_count":221},{"id":"1606.01933","title":"A Decomposable Attention Model for Natural Language Inference","created":"2016-06-06","cited_by_count":215},{"id":"1903.08983","title":"SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)","created":"2019-03-19","cited_by_count":207},{"id":"2101.00774","title":"Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering","created":"2021-01-04","cited_by_count":178},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151},{"id":"2006.07235","title":"SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)","created":"2020-06-12","cited_by_count":138},{"id":"1903.10318","title":"Fine-tune BERT for Extractive Summarization","created":"2019-03-25","cited_by_count":122},{"id":"2110.06733","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","created":"2021-10-13","cited_by_count":120},{"id":"2202.02950","title":"Jury Learning: Integrating Dissenting Voices into Machine Learning Models","created":"2022-02-07","cited_by_count":118},{"id":"2006.00998","title":"Toxicity Detection: Does Context Really Matter?","created":"2020-06-01","cited_by_count":93},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91},{"id":"2109.05704","title":"Mitigating Language-Dependent Ethnic Bias in BERT","created":"2021-09-13","cited_by_count":87},{"id":"1606.02821","title":"Cultural Shift or Linguistic Drift? Comparing Two Computational Measures of Semantic Change","created":"2016-06-09","cited_by_count":63},{"id":"1812.00978","title":"A Survey on Semantic Parsing","created":"2018-12-03","cited_by_count":62},{"id":"2003.07459","title":"Offensive Language Identification in Greek","created":"2020-03-16","cited_by_count":50},{"id":"1901.10457","title":"Universal Dependency Parsing from Scratch","created":"2019-01-29","cited_by_count":46},{"id":"2011.12631","title":"A Panoramic Survey of Natural Language Processing in the Arab World","created":"2020-11-25","cited_by_count":45},{"id":"2104.14694","title":"Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses","created":"2021-04-29","cited_by_count":39},{"id":"2008.12014","title":"GREEK-BERT: The Greeks visiting Sesame Street","created":"2020-08-27","cited_by_count":38},{"id":"1905.11471","title":"XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering","created":"2019-05-27","cited_by_count":35},{"id":"2010.08275","title":"It's not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT","created":"2020-10-16","cited_by_count":30},{"id":"1909.11291","title":"Question Answering is a Format; When is it Useful?","created":"2019-09-25","cited_by_count":25},{"id":"1906.02376","title":"Training Temporal Word Embeddings with a Compass","created":"2019-06-05","cited_by_count":23},{"id":"2105.05996","title":"Multilingual Offensive Language Identification for Low-resource Languages","created":"2021-05-12","cited_by_count":22},{"id":"2112.14330","title":"Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora","created":"2021-12-28","cited_by_count":21},{"id":"1903.02784","title":"Arabic natural language processing: An overview","created":"2019-03-07","cited_by_count":20},{"id":"2105.09825","title":"A comparative evaluation and analysis of three generations of Distributional Semantic Models","created":"2021-05-20","cited_by_count":19},{"id":"1705.09993","title":"Deep Learning for User Comment Moderation","created":"2017-05-28","cited_by_count":18},{"id":"2003.04642","title":"A Framework for Evaluation of Machine Reading Comprehension Gold Standards","created":"2020-03-10","cited_by_count":18},{"id":"2305.14996","title":"The ACL OCL Corpus: Advancing Open Science in Computational Linguistics","created":"2023-05-24","cited_by_count":17},{"id":"1810.13181","title":"WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community","created":"2018-10-31","cited_by_count":16},{"id":"2109.15298","title":"Multi-granular Legal Topic Classification on Greek Legislation","created":"2021-09-30","cited_by_count":15},{"id":"2107.03844","title":"A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models","created":"2021-07-08","cited_by_count":13},{"id":"2310.11923","title":"Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing","created":"2023-10-18","cited_by_count":12},{"id":"2010.03542","title":"Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification using Pre-trained Language Models","created":"2020-10-07","cited_by_count":11},{"id":"1708.03699","title":"Improved Abusive Comment Moderation with User Embeddings","created":"2017-08-11","cited_by_count":9},{"id":"1808.08538","title":"Nowcasting the Stance of Social Media Users in a Sudden Vote: The Case of the Greek Referendum","created":"2018-08-26","cited_by_count":8},{"id":"2008.01354","title":"NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer","created":"2020-08-04","cited_by_count":8},{"id":"2304.00869","title":"GreekBART: The First Pretrained Greek Sequence-to-Sequence Model","created":"2023-04-03","cited_by_count":8},{"id":"1810.06694","title":"Word Embeddings from Large-Scale Greek Web Content","created":"2018-10-08","cited_by_count":6},{"id":"2109.11326","title":"The Current State of Finnish NLP","created":"2021-09-23","cited_by_count":5},{"id":"2210.12883","title":"A Greek Parliament Proceedings Dataset for Computational Linguistics and Political Analysis","created":"2022-10-23","cited_by_count":4},{"id":"1904.04032","title":"Evaluation of Greek Word Embeddings","created":"2019-04-08","cited_by_count":3},{"id":"2102.00214","title":"Taxonomic survey of Hindi Language NLP systems","created":"2021-01-30","cited_by_count":3},{"id":"2103.15075","title":"PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation","created":"2021-03-28","cited_by_count":3},{"id":"2109.08794","title":"A Comprehensive Overview of Recommender System and Sentiment Analysis","created":"2021-09-18","cited_by_count":3},{"id":"2310.03193","title":"The Rise of Open Science: Tracking the Evolution and Perceived Value of Data and Methods Link-Sharing Practices","created":"2023-10-04","cited_by_count":3},{"id":"1902.03659","title":"Neural embeddings for metaphor detection in a corpus of Greek texts","created":"2019-02-10","cited_by_count":2},{"id":"1903.05440","title":"Market Trend Prediction using Sentiment Analysis: Lessons Learned and Paths Forward","created":"2019-03-13","cited_by_count":2},{"id":"1912.04965","title":"An Ensemble Method for Producing Word Representations focusing on the Greek Language","created":"2019-12-10","cited_by_count":2},{"id":"2112.01651","title":"Multi-modal application: Image Memes Generation","created":"2021-12-03","cited_by_count":2},{"id":"2208.01912","title":"Cross-Lingual Knowledge Transfer for Clinical Phenotyping","created":"2022-08-03","cited_by_count":2},{"id":"2311.07767","title":"GreekT5: A Series of Greek Sequence-to-Sequence Models for News Summarization","created":"2023-11-13","cited_by_count":2},{"id":"1912.10162","title":"Design and implementation of an open source Greek POS Tagger and Entity Recognizer using spaCy","created":"2019-12-05","cited_by_count":1},{"id":"2211.02415","title":"Multilingual Name Entity Recognition and Intent Classification Employing Deep Learning Architectures","created":"2022-11-04","cited_by_count":1}],"next_cursor":null}