{"list":"other","total":54,"rows":[{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"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":"2010.11125","title":"Beyond English-Centric Multilingual Machine Translation","created":"2020-10-21","cited_by_count":561},{"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":"2010.12309","title":"A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios","created":"2020-10-23","cited_by_count":171},{"id":"2103.11811","title":"MasakhaNER: Named Entity Recognition for African Languages","created":"2021-03-22","cited_by_count":155},{"id":"2204.06487","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","created":"2022-04-13","cited_by_count":149},{"id":"1705.00440","title":"Data Augmentation for Low-Resource Neural Machine Translation","created":"2017-05-01","cited_by_count":139},{"id":"2010.12858","title":"When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models","created":"2020-10-24","cited_by_count":131},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92},{"id":"2006.07264","title":"Low-resource Languages: A Review of Past Work and Future Challenges","created":"2020-06-12","cited_by_count":91},{"id":"2201.08277","title":"NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis","created":"2022-01-20","cited_by_count":64},{"id":"2108.03265","title":"Facebook AI WMT21 News Translation Task Submission","created":"2021-08-06","cited_by_count":57},{"id":"2203.08351","title":"Towards Afrocentric NLP for African Languages: Where We Are and Where We Can Go","created":"2022-03-16","cited_by_count":47},{"id":"2211.03263","title":"AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages","created":"2022-11-07","cited_by_count":46},{"id":"2406.03368","title":"IrokoBench: A New Benchmark for African Languages in the Age of Large Language Models","created":"2024-06-05","cited_by_count":43},{"id":"2406.16678","title":"Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation","created":"2024-06-24","cited_by_count":41},{"id":"2210.11744","title":"AfroLID: A Neural Language Identification Tool for African Languages","created":"2022-10-21","cited_by_count":39},{"id":"2408.04303","title":"Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP","created":"2024-08-08","cited_by_count":36},{"id":"1912.02481","title":"Massive vs. Curated Word Embeddings for Low-Resourced Languages. The Case of Yor\\`ub\\'a and Twi","created":"2019-12-05","cited_by_count":33},{"id":"1709.03856","title":"StarSpace: Embed All The Things!","created":"2017-09-12","cited_by_count":24},{"id":"2311.01108","title":"Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance","created":"2023-11-02","cited_by_count":24},{"id":"2103.07762","title":"OkwuGb\\'e: End-to-End Speech Recognition for Fon and Igbo","created":"2021-03-13","cited_by_count":13},{"id":"2205.01133","title":"Hausa Visual Genome: A Dataset for Multi-Modal English to Hausa Machine Translation","created":"2022-05-02","cited_by_count":13},{"id":"2409.00626","title":"Correcting FLORES Evaluation Dataset for Four African Languages","created":"2024-09-01","cited_by_count":13},{"id":"2305.17690","title":"HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language","created":"2023-05-28","cited_by_count":12},{"id":"2410.20817","title":"The Zeno's Paradox of `Low-Resource' Languages","created":"2024-10-28","cited_by_count":12},{"id":"1804.00832","title":"Attentive Sequence-to-Sequence Learning for Diacritic Restoration of Yor\\`ub\\'a Language Text","created":"2018-04-03","cited_by_count":11},{"id":"2105.00810","title":"NaijaNER : Comprehensive Named Entity Recognition for 5 Nigerian Languages","created":"2021-03-30","cited_by_count":10},{"id":"2403.19260","title":"NaijaHate: Evaluating Hate Speech Detection on Nigerian Twitter Using Representative Data","created":"2024-03-28","cited_by_count":10},{"id":"2102.06991","title":"The first large scale collection of diverse Hausa language datasets","created":"2021-02-13","cited_by_count":6},{"id":"1911.10708","title":"hauWE: Hausa Words Embedding for Natural Language Processing","created":"2019-11-25","cited_by_count":5},{"id":"2003.10564","title":"Improving Yor\\`ub\\'a Diacritic Restoration","created":"2020-03-23","cited_by_count":5},{"id":"2006.05014","title":"HausaMT v1.0: Towards English-Hausa Neural Machine Translation","created":"2020-06-09","cited_by_count":5},{"id":"2103.04225","title":"Translating the Unseen? Yoruba-English MT in Low-Resource, Morphologically-Unmarked Settings","created":"2021-03-07","cited_by_count":5},{"id":"2103.09185","title":"A Multilingual African Embedding for FAQ Chatbots","created":"2021-03-16","cited_by_count":5},{"id":"2308.09768","title":"NaijaRC: A Multi-choice Reading Comprehension Dataset for Nigerian Languages","created":"2023-08-18","cited_by_count":4},{"id":"2311.10541","title":"Detection and Analysis of Offensive Online Content in Hausa Language","created":"2023-11-17","cited_by_count":4},{"id":"2410.18390","title":"Monolingual and Multilingual Misinformation Detection for Low-Resource Languages: A Comprehensive Survey","created":"2024-10-24","cited_by_count":4},{"id":"2003.08370","title":"Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yor\\`ub\\'a","created":"2020-03-18","cited_by_count":3},{"id":"2004.14176","title":"Development of a General Purpose Sentiment Lexicon for Igbo Language","created":"2020-04-24","cited_by_count":3},{"id":"2011.07605","title":"The Challenge of Diacritics in Yoruba Embeddings","created":"2020-11-15","cited_by_count":3},{"id":"2304.07542","title":"Machine Learning Research Trends in Africa: A 30 Years Overview with Bibliometric Analysis Review","created":"2023-04-15","cited_by_count":3},{"id":"2304.13634","title":"HausaNLP at SemEval-2023 Task 12: Leveraging African Low Resource TweetData for Sentiment Analysis","created":"2023-04-26","cited_by_count":3},{"id":"2401.11617","title":"The State of Computer Vision Research in Africa","created":"2024-01-21","cited_by_count":3},{"id":"2405.19575","title":"A Deep Convolutional Neural Network-based Model for Aspect and Polarity Classification in Hausa Movie Reviews","created":"2024-05-29","cited_by_count":3},{"id":"1903.05225","title":"Bootstrapping Method for Developing Part-of-Speech Tagged Corpus in Low Resource Languages Tagset - A Focus on an African Igbo","created":"2019-03-12","cited_by_count":1},{"id":"2009.06376","title":"Analysis and representation of Igbo text document for a text-based system","created":"2020-09-05","cited_by_count":1},{"id":"2401.13398","title":"Text Categorization Can Enhance Domain-Agnostic Stopword Extraction","created":"2024-01-24","cited_by_count":1}],"next_cursor":null}