{"total":18,"rows":[{"id":"2201.06642","title":"Towards a Cleaner Document-Oriented Multilingual Crawled Corpus","created":"2022-01-17","cited_by_count":143,"area":null},{"id":"2107.05295","title":"DaCy: A Unified Framework for Danish NLP","created":"2021-07-12","cited_by_count":10,"area":null},{"id":"2307.05083","title":"Vacaspati: A Diverse Corpus of Bangla Literature","created":"2023-07-11","cited_by_count":10,"area":null},{"id":"2111.06916","title":"Offense Detection in Dravidian Languages using Code-Mixing Index based Focal Loss","created":"2021-11-12","cited_by_count":6,"area":null},{"id":"2105.09611","title":"Dependency Parsing with Bottom-up Hierarchical Pointer Networks","created":"2021-05-20","cited_by_count":5,"area":null},{"id":"2108.09814","title":"UzBERT: pretraining a BERT model for Uzbek","created":"2021-08-22","cited_by_count":5,"area":null},{"id":"2309.06163","title":"Overview of GUA-SPA at IberLEF 2023: Guarani-Spanish Code Switching Analysis","created":"2023-09-12","cited_by_count":5,"area":null},{"id":"2310.13029","title":"Blending gradient boosted trees and neural networks for point and probabilistic forecasting of hierarchical time series","created":"2023-10-19","cited_by_count":5,"area":null},{"id":"2102.13514","title":"Learning to Make Compiler Optimizations More Effective","created":"2021-02-24","cited_by_count":4,"area":null},{"id":"2403.05065","title":"Can we obtain significant success in RST discourse parsing by using Large Language Models?","created":"2024-03-08","cited_by_count":4,"area":null},{"id":"2106.03379","title":"LAWDR: Language-Agnostic Weighted Document Representations from Pre-trained Models","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2209.02139","title":"Cross-Lingual and Cross-Domain Crisis Classification for Low-Resource Scenarios","created":"2022-09-05","cited_by_count":3,"area":null},{"id":"2104.07951","title":"Optimal Size-Performance Tradeoffs: Weighing PoS Tagger Models","created":"2021-04-16","cited_by_count":2,"area":null},{"id":"2506.15372","title":"COSMMIC: Comment-Sensitive Multimodal Multilingual Indian Corpus for Summarization and Headline Generation","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2604.20835","title":"Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2602.19174","title":"TurkicNLP: An NLP Toolkit for Turkic Languages","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2105.05605","title":"Priberam Labs at the NTCIR-15 SHINRA2020-ML: Classification Task","created":"2021-05-12","cited_by_count":0,"area":null},{"id":"2310.14384","title":"ARCOQ: Arabic Closest Opposite Questions Dataset","created":"2023-10-22","cited_by_count":0,"area":null}],"next_cursor":null}