{"list":"other","total":53,"rows":[{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"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":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"id":"2106.13822","title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","created":"2021-06-25","cited_by_count":347},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293},{"id":"1812.09449","title":"A Survey on Deep Learning for Named Entity Recognition","created":"2018-12-22","cited_by_count":282},{"id":"2004.10643","title":"Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection","created":"2020-04-22","cited_by_count":271},{"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":"2203.17189","title":"Scaling Up Models and Data with $\\texttt{t5x}$ and $\\texttt{seqio}$","created":"2022-03-31","cited_by_count":187},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168},{"id":"2010.02353","title":"Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages","created":"2020-10-05","cited_by_count":159},{"id":"2008.09335","title":"MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark","created":"2020-08-21","cited_by_count":158},{"id":"2103.11811","title":"MasakhaNER: Named Entity Recognition for African Languages","created":"2021-03-22","cited_by_count":155},{"id":"2010.11856","title":"XOR QA: Cross-lingual Open-Retrieval Question Answering","created":"2020-10-22","cited_by_count":121},{"id":"2110.06733","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","created":"2021-10-13","cited_by_count":120},{"id":"2209.15003","title":"Compositional Semantic Parsing with Large Language Models","created":"2022-09-29","cited_by_count":95},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92},{"id":"1803.04014","title":"NVIDIA Tensor Core Programmability, Performance & Precision","created":"2018-03-11","cited_by_count":79},{"id":"2010.14571","title":"Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus","created":"2020-10-27","cited_by_count":77},{"id":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69},{"id":"2205.15960","title":"NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages","created":"2022-05-31","cited_by_count":68},{"id":"2302.08956","title":"AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages","created":"2023-02-17","cited_by_count":68},{"id":"2201.08277","title":"NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis","created":"2022-01-20","cited_by_count":64},{"id":"2106.02787","title":"BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling","created":"2021-06-05","cited_by_count":56},{"id":"2010.03179","title":"Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages","created":"2020-10-07","cited_by_count":52},{"id":"2012.15682","title":"A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters","created":"2020-12-31","cited_by_count":45},{"id":"2210.12391","title":"MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition","created":"2022-10-22","cited_by_count":38},{"id":"2004.14958","title":"A Call for More Rigor in Unsupervised Cross-lingual Learning","created":"2020-04-30","cited_by_count":37},{"id":"1804.06826","title":"Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking","created":"2018-04-18","cited_by_count":35},{"id":"2007.01176","title":"Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset","created":"2020-07-02","cited_by_count":35},{"id":"2008.06788","title":"Is Supervised Syntactic Parsing Beneficial for Language Understanding? An Empirical Investigation","created":"2020-08-15","cited_by_count":34},{"id":"2010.12174","title":"KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi","created":"2020-10-23","cited_by_count":31},{"id":"2011.05402","title":"OCR Post Correction for Endangered Language Texts","created":"2020-11-10","cited_by_count":31},{"id":"2110.07679","title":"GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems","created":"2021-10-14","cited_by_count":31},{"id":"2201.13405","title":"Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation","created":"2022-01-31","cited_by_count":23},{"id":"2303.08954","title":"PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs","created":"2023-03-15","cited_by_count":16},{"id":"2212.10455","title":"MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-12-20","cited_by_count":15},{"id":"1909.09756","title":"Scale MLPerf-0.6 models on Google TPU-v3 Pods","created":"2019-09-21","cited_by_count":14},{"id":"2210.10027","title":"Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR","created":"2022-10-18","cited_by_count":13},{"id":"2111.02622","title":"Lexically Aware Semi-Supervised Learning for OCR Post-Correction","created":"2021-11-04","cited_by_count":12},{"id":"2202.13274","title":"OCR Improves Machine Translation for Low-Resource Languages","created":"2022-02-27","cited_by_count":5},{"id":"2212.06346","title":"The Massively Multilingual Natural Language Understanding 2022 (MMNLU-22) Workshop and Competition","created":"2022-12-13","cited_by_count":3},{"id":"2301.11406","title":"Beyond Arabic: Software for Perso-Arabic Script Manipulation","created":"2023-01-26","cited_by_count":2},{"id":"2206.10254","title":"Towards Optimizing OCR for Accessibility","created":"2022-06-21","cited_by_count":1}],"next_cursor":null}