{"total":171,"rows":[{"id":"2304.01904","title":"REFINER: Reasoning Feedback on Intermediate Representations","created":"2023-04-04","cited_by_count":205,"area":"lr"},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123,"area":null},{"id":"2108.13897","title":"mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset","created":"2021-08-31","cited_by_count":116,"area":null},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101,"area":null},{"id":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"area":null},{"id":"2210.08523","title":"Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP World","created":"2022-10-16","cited_by_count":55,"area":null},{"id":"2403.11009","title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages","created":"2024-03-16","cited_by_count":50,"area":null},{"id":"2104.05514","title":"Self-Training with Weak Supervision","created":"2021-04-12","cited_by_count":49,"area":null},{"id":"2104.06951","title":"Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey","created":"2021-04-14","cited_by_count":46,"area":null},{"id":"2204.08143","title":"Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learning","created":"2022-04-18","cited_by_count":41,"area":null},{"id":"2306.08620","title":"Anticipatory Music Transformer","created":"2023-06-14","cited_by_count":36,"area":null},{"id":"2104.08524","title":"Multilingual and Cross-Lingual Intent Detection from Spoken Data","created":"2021-04-17","cited_by_count":35,"area":null},{"id":"2306.07200","title":"Fill-Up: Balancing Long-Tailed Data with Generative Models","created":"2023-06-12","cited_by_count":34,"area":null},{"id":"2403.02990","title":"Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges","created":"2024-03-05","cited_by_count":30,"area":null},{"id":"2412.04497","title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","created":"2024-11-30","cited_by_count":27,"area":null},{"id":"2111.02705","title":"Benchmarking Multimodal AutoML for Tabular Data with Text Fields","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2210.12814","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","created":"2022-10-23","cited_by_count":26,"area":null},{"id":"2210.15452","title":"Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity","created":"2022-10-20","cited_by_count":25,"area":null},{"id":"2309.05092","title":"Adaptive conformal classification with noisy labels","created":"2023-09-10","cited_by_count":25,"area":null},{"id":"2204.09371","title":"Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification","created":"2022-04-20","cited_by_count":21,"area":null},{"id":"2210.04675","title":"A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing","created":"2022-10-10","cited_by_count":21,"area":null},{"id":"2408.17024","title":"InkubaLM: A small language model for low-resource African languages","created":"2024-08-30","cited_by_count":18,"area":null},{"id":"2104.08570","title":"Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems","created":"2021-04-17","cited_by_count":17,"area":null},{"id":"2302.12578","title":"Fairness in Language Models Beyond English: Gaps and Challenges","created":"2023-02-24","cited_by_count":16,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2101.09763","title":"Analysing the Noise Model Error for Realistic Noisy Label Data","created":"2021-01-24","cited_by_count":14,"area":null},{"id":"2111.02674","title":"Voice Conversion Can Improve ASR in Very Low-Resource Settings","created":"2021-11-04","cited_by_count":14,"area":null},{"id":"2203.08118","title":"Representation Learning for Resource-Constrained Keyphrase Generation","created":"2022-03-15","cited_by_count":14,"area":null},{"id":"2208.03197","title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","created":"2022-08-05","cited_by_count":14,"area":null},{"id":"2305.13047","title":"Automated stance detection in complex topics and small languages: the challenging case of immigration in polarizing news media","created":"2023-05-22","cited_by_count":14,"area":null},{"id":"2410.13153","title":"Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2203.03691","title":"HyperMixer: An MLP-based Low Cost Alternative to Transformers","created":"2022-03-07","cited_by_count":13,"area":null},{"id":"2401.04716","title":"Low-Resource Vision Challenges for Foundation Models","created":"2024-01-09","cited_by_count":13,"area":null},{"id":"2111.09618","title":"To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP","created":"2021-11-18","cited_by_count":12,"area":null},{"id":"2302.06868","title":"SwitchPrompt: Learning Domain-Specific Gated Soft Prompts for Classification in Low-Resource Domains","created":"2023-02-14","cited_by_count":12,"area":null},{"id":"2411.17637","title":"On Limitations of LLM as Annotator for Low Resource Languages","created":"2024-11-26","cited_by_count":12,"area":null},{"id":"2504.16977","title":"Tokenization Matters: Improving Zero-Shot NER for Indic Languages","created":"2025-04-23","cited_by_count":12,"area":null},{"id":"2104.08078","title":"To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning","created":"2021-04-16","cited_by_count":11,"area":null},{"id":"2209.12577","title":"Meta-Learning a Cross-lingual Manifold for Semantic Parsing","created":"2022-09-26","cited_by_count":11,"area":null},{"id":"2202.08063","title":"Information Extraction in Low-Resource Scenarios: Survey and Perspective","created":"2022-02-16","cited_by_count":10,"area":null},{"id":"2203.07735","title":"Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation","created":"2022-03-15","cited_by_count":10,"area":null},{"id":"2304.02737","title":"Efficient OCR for Building a Diverse Digital History","created":"2023-04-05","cited_by_count":10,"area":null},{"id":"2305.00090","title":"NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysis","created":"2023-04-28","cited_by_count":10,"area":null},{"id":"2305.14716","title":"GlobalBench: A Benchmark for Global Progress in Natural Language Processing","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2312.01314","title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","created":"2023-12-03","cited_by_count":9,"area":null},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","cited_by_count":9,"area":null},{"id":"2405.09335","title":"Prompting-based Synthetic Data Generation for Few-Shot Question Answering","created":"2024-05-15","cited_by_count":9,"area":"synth"},{"id":"2405.09913","title":"TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data","created":"2024-05-16","cited_by_count":9,"area":null},{"id":"2203.12524","title":"Computational historical linguistics and language diversity in South Asia","created":"2022-03-23","cited_by_count":8,"area":null},{"id":"2204.04813","title":"Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2205.09744","title":"Overcoming Language Disparity in Online Content Classification with Multimodal Learning","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2205.15550","title":"A Multi-level Supervised Contrastive Learning Framework for Low-Resource Natural Language Inference","created":"2022-05-31","cited_by_count":8,"area":null},{"id":"2303.15587","title":"Linguistically Informed ChatGPT Prompts to Enhance Japanese-Chinese Machine Translation: A Case Study on Attributive Clauses","created":"2023-03-27","cited_by_count":8,"area":null},{"id":"2504.07749","title":"NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark","created":"2025-04-10","cited_by_count":8,"area":null},{"id":"2201.01337","title":"ZeroBERTo: Leveraging Zero-Shot Text Classification by Topic Modeling","created":"2022-01-04","cited_by_count":7,"area":null},{"id":"2205.10399","title":"Multilingual Normalization of Temporal Expressions with Masked Language Models","created":"2022-05-20","cited_by_count":7,"area":null},{"id":"2301.08937","title":"Exploring Methods for Building Dialects-Mandarin Code-Mixing Corpora: A Case Study in Taiwanese Hokkien","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2410.03576","title":"Table Question Answering for Low-resourced Indic Languages","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2410.09948","title":"State of NLP in Kenya: A Survey","created":"2024-10-13","cited_by_count":7,"area":null},{"id":"2111.01340","title":"Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks","created":"2021-11-02","cited_by_count":6,"area":null},{"id":"2305.12717","title":"TADA: Efficient Task-Agnostic Domain Adaptation for Transformers","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2310.15269","title":"GradSim: Gradient-Based Language Grouping for Effective Multilingual Training","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2407.01411","title":"HyperLoader: Integrating Hypernetwork-Based LoRA and Adapter Layers into Multi-Task Transformers for Sequence Labelling","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2501.17830","title":"A Comprehensive Survey on Legal Summarization: Challenges and Future Directions","created":"2025-01-29","cited_by_count":6,"area":null},{"id":"2509.11570","title":"Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challenges","created":"2025-09-15","cited_by_count":6,"area":null},{"id":"2112.13634","title":"A Survey on non-English Question Answering Dataset","created":"2021-12-27","cited_by_count":5,"area":null},{"id":"2202.00470","title":"An Assessment of the Impact of OCR Noise on Language Models","created":"2022-01-26","cited_by_count":5,"area":null},{"id":"2211.14880","title":"Combining Data Generation and Active Learning for Low-Resource Question Answering","created":"2022-11-27","cited_by_count":5,"area":null},{"id":"2305.00606","title":"Low-Resourced Machine Translation for Senegalese Wolof Language","created":"2023-05-01","cited_by_count":5,"area":null},{"id":"2310.10583","title":"Who Are All The Stochastic Parrots Imitating? They Should Tell Us!","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2310.18046","title":"ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese","created":"2023-10-27","cited_by_count":5,"area":"lr"},{"id":"2403.09428","title":"Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity","created":"2024-03-14","cited_by_count":5,"area":null},{"id":"2409.04512","title":"Chain-of-Translation Prompting (CoTR): A Novel Prompting Technique for Low Resource Languages","created":"2024-09-06","cited_by_count":5,"area":null},{"id":"2510.08962","title":"Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2306.14806","title":"A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling","created":"2023-06-26","cited_by_count":4,"area":null},{"id":"2308.02234","title":"Sinhala-English Parallel Word Dictionary Dataset","created":"2023-08-04","cited_by_count":4,"area":null},{"id":"2402.02078","title":"Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varieties","created":"2024-02-03","cited_by_count":4,"area":null},{"id":"2403.09721","title":"A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2404.01490","title":"AAdaM at SemEval-2024 Task 1: Augmentation and Adaptation for Multilingual Semantic Textual Relatedness","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2406.02601","title":"Multimodal Deep Learning for Low-Resource Settings: A Vector Embedding Alignment Approach for Healthcare Applications","created":"2024-06-02","cited_by_count":4,"area":null},{"id":"2407.15339","title":"Deep Learning for Economists","created":"2024-07-22","cited_by_count":4,"area":null},{"id":"2411.09539","title":"Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2412.10008","title":"Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language","created":"2024-12-13","cited_by_count":4,"area":null},{"id":"2506.05387","title":"Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2105.12530","title":"Deception detection in text and its relation to the cultural dimension of individualism/collectivism","created":"2021-05-26","cited_by_count":3,"area":null},{"id":"2112.09860","title":"Morpheme Boundary Detection & Grammatical Feature Prediction for Gujarati : Dataset & Model","created":"2021-12-18","cited_by_count":3,"area":null},{"id":"2201.11374","title":"Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing","created":"2022-01-27","cited_by_count":3,"area":null},{"id":"2502.11364","title":"Blessing of Multilinguality: A Systematic Analysis of Multilingual In-Context Learning","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2504.19856","title":"Efficient Domain-adaptive Continual Pretraining for the Process Industry in the German Language","created":"2025-04-28","cited_by_count":3,"area":null},{"id":"2601.14894","title":"To Neuro-Symbolic Classification and Beyond by Compiling Description Logic Ontologies to Probabilistic Circuits","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2201.01845","title":"Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation","created":"2022-01-05","cited_by_count":2,"area":null},{"id":"2302.11412","title":"Data Augmentation for Neural NLP","created":"2023-02-22","cited_by_count":2,"area":null},{"id":"2304.01319","title":"Approaches to Corpus Creation for Low-Resource Language Technology: the Case of Southern Kurdish and Laki","created":"2023-04-03","cited_by_count":2,"area":null},{"id":"2304.09957","title":"Low-resource Bilingual Dialect Lexicon Induction with Large Language Models","created":"2023-04-19","cited_by_count":2,"area":null},{"id":"2308.01785","title":"Lexicon and Rule-based Word Lemmatization Approach for the Somali Language","created":"2023-08-03","cited_by_count":2,"area":null},{"id":"2407.17479","title":"The #Somos600M Project: Generating NLP resources that represent the diversity of the languages from LATAM, the Caribbean, and Spain","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2412.09922","title":"Low-Resource Fast Text Classification Based on Intra-Class and Inter-Class Distance Calculation","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2501.03870","title":"Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection","created":"2025-01-07","cited_by_count":2,"area":null}],"next_cursor":"100"}