{"total":23,"rows":[{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148,"area":null},{"id":"2103.10069","title":"Constructive and Toxic Speech Detection for Open-domain Social Media Comments in Vietnamese","created":"2021-03-18","cited_by_count":17,"area":null},{"id":"2105.15079","title":"SA2SL: From Aspect-Based Sentiment Analysis to Social Listening System for Business Intelligence","created":"2021-05-31","cited_by_count":12,"area":null},{"id":"2310.11166","title":"ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing","created":"2023-10-17","cited_by_count":11,"area":null},{"id":"2403.15882","title":"VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding","created":"2024-03-23","cited_by_count":8,"area":null},{"id":"2209.10482","title":"SMTCE: A Social Media Text Classification Evaluation Benchmark and BERTology Models for Vietnamese","created":"2022-09-21","cited_by_count":7,"area":null},{"id":"2403.02715","title":"Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models","created":"2024-03-05","cited_by_count":6,"area":null},{"id":"2104.11969","title":"Vietnamese Complaint Detection on E-Commerce Websites","created":"2021-04-24","cited_by_count":4,"area":null},{"id":"2310.14557","title":"The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2412.01186","title":"SailCompass: Towards Reproducible and Robust Evaluation for Southeast Asian Languages","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2210.02063","title":"Improving Sentiment Analysis By Emotion Lexicon Approach on Vietnamese Texts","created":"2022-10-05","cited_by_count":2,"area":null},{"id":"2508.12243","title":"SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?","created":"2025-08-17","cited_by_count":2,"area":null},{"id":"2110.07833","title":"Span Detection for Aspect-Based Sentiment Analysis in Vietnamese","created":"2021-10-15","cited_by_count":1,"area":null},{"id":"2309.02902","title":"ViCGCN: Graph Convolutional Network with Contextualized Language Models for Social Media Mining in Vietnamese","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2401.16403","title":"ViLexNorm: A Lexical Normalization Corpus for Vietnamese Social Media Text","created":"2024-01-29","cited_by_count":1,"area":null},{"id":"2409.20467","title":"A Weakly Supervised Data Labeling Framework for Machine Lexical Normalization in Vietnamese Social Media","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2503.07470","title":"Advancing Vietnamese Information Retrieval with Learning Objective and Benchmark","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2301.00418","title":"Is word segmentation necessary for Vietnamese sentiment classification?","created":"2023-01-01","cited_by_count":0,"area":null},{"id":"2405.00543","title":"New Benchmark Dataset and Fine-Grained Cross-Modal Fusion Framework for Vietnamese Multimodal Aspect-Category Sentiment Analysis","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2602.08371","title":"ViGoEmotions: A Benchmark Dataset For Fine-grained Emotion Detection on Vietnamese Texts","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2608.03095","title":"VIVID: A Culturally Grounded Benchmark Exposing the Figurative Language Gap in Vietnamese NLP","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.10414","title":"How Robust Are LLMs to Vietnamese Dialects?","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.12776","title":"ViTOED: A Dataset for Target-Oriented Emotion Detection on Vietnamese Social Media Texts","created":"2026-08-13","cited_by_count":0,"area":null}],"next_cursor":null}