{"total":27,"rows":[{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168,"area":null},{"id":"2103.11811","title":"MasakhaNER: Named Entity Recognition for African Languages","created":"2021-03-22","cited_by_count":155,"area":null},{"id":"2106.00641","title":"SpanNER: Named Entity Re-/Recognition as Span Prediction","created":"2021-06-01","cited_by_count":55,"area":null},{"id":"2104.06387","title":"ExplainaBoard: An Explainable Leaderboard for NLP","created":"2021-04-13","cited_by_count":50,"area":null},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2102.05486","title":"Towards More Fine-grained and Reliable NLP Performance Prediction","created":"2021-02-10","cited_by_count":26,"area":null},{"id":"2404.16958","title":"A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice","created":"2024-04-25","cited_by_count":26,"area":null},{"id":"2111.08546","title":"Interpreting Language Models Through Knowledge Graph Extraction","created":"2021-11-16","cited_by_count":14,"area":null},{"id":"2205.00034","title":"What do we Really Know about State of the Art NER?","created":"2022-04-29","cited_by_count":10,"area":null},{"id":"2210.09163","title":"KPI-EDGAR: A Novel Dataset and Accompanying Metric for Relation Extraction from Financial Documents","created":"2022-10-17","cited_by_count":9,"area":null},{"id":"2202.12875","title":"DataLab: A Platform for Data Analysis and Intervention","created":"2022-02-25","cited_by_count":8,"area":null},{"id":"2205.15575","title":"hmBERT: Historical Multilingual Language Models for Named Entity Recognition","created":"2022-05-31","cited_by_count":8,"area":null},{"id":"2101.00160","title":"How Do Your Biomedical Named Entity Recognition Models Generalize to Novel Entities?","created":"2021-01-01","cited_by_count":7,"area":null},{"id":"2204.14264","title":"Polyglot Prompt: Multilingual Multitask PrompTraining","created":"2022-04-29","cited_by_count":6,"area":null},{"id":"2104.07249","title":"Regularization for Long Named Entity Recognition","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2104.04434","title":"Larger-Context Tagging: When and Why Does It Work?","created":"2021-04-09","cited_by_count":4,"area":null},{"id":"2109.12008","title":"Separating Retention from Extraction in the Evaluation of End-to-end Relation Extraction","created":"2021-09-24","cited_by_count":2,"area":null},{"id":"2207.03300","title":"Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognition","created":"2022-07-07","cited_by_count":2,"area":null},{"id":"2212.09272","title":"Statistical Dataset Evaluation: Reliability, Difficulty, and Validity","created":"2022-12-19","cited_by_count":2,"area":null},{"id":"2210.12949","title":"Enhancing Label Consistency on Document-level Named Entity Recognition","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2308.02951","title":"Multi-Source (Pre-)Training for Cross-Domain Measurement, Unit and Context Extraction","created":"2023-08-05","cited_by_count":1,"area":null},{"id":"2201.09523","title":"BTPK-based interpretable method for NER tasks based on Talmudic Public Announcement Logic","created":"2022-01-24","cited_by_count":0,"area":null},{"id":"2307.07134","title":"Multi-Dimensional Ability Diagnosis for Machine Learning Algorithms","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2410.05046","title":"Named Clinical Entity Recognition Benchmark","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2602.12759","title":"Towards a Diagnostic and Predictive Evaluation Methodology for Sequence Labeling Tasks","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2610.00007","title":"On-Device Named-Entity Recognition: A Deployability Study of Accuracy, Cost, Reliability, and Confidence","created":"2026-07-09","cited_by_count":0,"area":null}],"next_cursor":null}