{"total":144,"rows":[{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92,"area":null},{"id":"2109.04650","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","created":"2021-09-10","cited_by_count":76,"area":null},{"id":"2101.03289","title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","created":"2021-01-09","cited_by_count":68,"area":null},{"id":"2202.01159","title":"L3Cube-MahaCorpus and MahaBERT: Marathi Monolingual Corpus, Marathi BERT Language Models, and Resources","created":"2022-02-02","cited_by_count":51,"area":null},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2205.06457","title":"ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation","created":"2022-05-13","cited_by_count":37,"area":null},{"id":"2107.07253","title":"MarIA: Spanish Language Models","created":"2021-07-15","cited_by_count":36,"area":null},{"id":"2109.09701","title":"BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese","created":"2021-09-20","cited_by_count":34,"area":null},{"id":"2312.13951","title":"Typhoon: Thai Large Language Models","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2309.10931","title":"A Family of Pretrained Transformer Language Models for Russian","created":"2023-09-19","cited_by_count":27,"area":null},{"id":"2212.13492","title":"MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsing","created":"2022-12-27","cited_by_count":22,"area":null},{"id":"2104.06546","title":"Large-Scale Contextualised Language Modelling for Norwegian","created":"2021-04-13","cited_by_count":21,"area":null},{"id":"2104.02021","title":"Intent Detection and Slot Filling for Vietnamese","created":"2021-04-05","cited_by_count":19,"area":null},{"id":"2104.03879","title":"COVID-19 Named Entity Recognition for Vietnamese","created":"2021-04-08","cited_by_count":19,"area":null},{"id":"2304.07880","title":"Sabi\\'a: Portuguese Large Language Models","created":"2023-04-16","cited_by_count":19,"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":"2204.08669","title":"Mono vs Multilingual BERT for Hate Speech Detection and Text Classification: A Case Study in Marathi","created":"2022-04-19","cited_by_count":16,"area":null},{"id":"2208.07864","title":"BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification","created":"2022-08-16","cited_by_count":16,"area":null},{"id":"2305.19709","title":"XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech","created":"2023-05-31","cited_by_count":16,"area":null},{"id":"2404.09296","title":"Cross-Data Knowledge Graph Construction for LLM-enabled Educational Question-Answering System: A Case Study at HCMUT","created":"2024-04-14","cited_by_count":14,"area":null},{"id":"2101.01476","title":"PhoNLP: A joint multi-task learning model for Vietnamese part-of-speech tagging, named entity recognition and dependency parsing","created":"2021-01-05","cited_by_count":13,"area":null},{"id":"2107.03844","title":"A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models","created":"2021-07-08","cited_by_count":13,"area":null},{"id":"2301.10186","title":"ViHOS: Hate Speech Spans Detection for Vietnamese","created":"2023-01-24","cited_by_count":13,"area":null},{"id":"2301.10439","title":"ViDeBERTa: A powerful pre-trained language model for Vietnamese","created":"2023-01-25","cited_by_count":11,"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":"2105.09043","title":"Sentence Extraction-Based Machine Reading Comprehension for Vietnamese","created":"2021-05-19","cited_by_count":9,"area":null},{"id":"2204.10717","title":"A Summary of the ALQAC 2021 Competition","created":"2022-04-22","cited_by_count":9,"area":null},{"id":"2206.00524","title":"Vietnamese Hate and Offensive Detection using PhoBERT-CNN and Social Media Streaming Data","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2503.07920","title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2311.02945","title":"PhoGPT: Generative Pre-training for Vietnamese","created":"2023-11-06","cited_by_count":8,"area":null},{"id":"2403.13737","title":"EthioLLM: Multilingual Large Language Models for Ethiopian Languages with Task Evaluation","created":"2024-03-20","cited_by_count":8,"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":"2105.01542","title":"Conversational Machine Reading Comprehension for Vietnamese Healthcare Texts","created":"2021-05-04","cited_by_count":7,"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":"2102.02111","title":"Introduction to Neural Transfer Learning with Transformers for Social Science Text Analysis","created":"2021-02-03","cited_by_count":6,"area":null},{"id":"2108.13741","title":"Monolingual versus Multilingual BERTology for Vietnamese Extractive Multi-Document Summarization","created":"2021-08-31","cited_by_count":6,"area":null},{"id":"2410.21321","title":"User-Aware Multilingual Abusive Content Detection in Social Media","created":"2024-10-26","cited_by_count":6,"area":null},{"id":"2109.01942","title":"On the ability of monolingual models to learn language-agnostic representations","created":"2021-09-04","cited_by_count":5,"area":null},{"id":"2206.09600","title":"SPBERTQA: A Two-Stage Question Answering System Based on Sentence Transformers for Medical Texts","created":"2022-06-20","cited_by_count":5,"area":null},{"id":"2307.15335","title":"BARTPhoBEiT: Pre-trained Sequence-to-Sequence and Image Transformers Models for Vietnamese Visual Question Answering","created":"2023-07-28","cited_by_count":5,"area":null},{"id":"2101.12672","title":"NLPBK at VLSP-2020 shared task: Compose transformer pretrained models for Reliable Intelligence Identification on Social network","created":"2021-01-29","cited_by_count":4,"area":null},{"id":"2103.09519","title":"Investigating Monolingual and Multilingual BERTModels for Vietnamese Aspect Category Detection","created":"2021-03-17","cited_by_count":4,"area":null},{"id":"2104.11969","title":"Vietnamese Complaint Detection on E-Commerce Websites","created":"2021-04-24","cited_by_count":4,"area":null},{"id":"2207.14636","title":"Detecting Spam Reviews on Vietnamese E-commerce Websites","created":"2022-07-27","cited_by_count":4,"area":null},{"id":"2209.06668","title":"UIT-ViCoV19QA: A Dataset for COVID-19 Community-based Question Answering on Vietnamese Language","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2210.05598","title":"Enriching Biomedical Knowledge for Low-resource Language Through Large-Scale Translation","created":"2022-10-11","cited_by_count":4,"area":null},{"id":"2403.08035","title":"Harnessing Artificial Intelligence to Combat Online Hate: Exploring the Challenges and Opportunities of Large Language Models in Hate Speech Detection","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2404.12618","title":"CORI: CJKV Benchmark with Romanization Integration -- A step towards Cross-lingual Transfer Beyond Textual Scripts","created":"2024-04-19","cited_by_count":4,"area":null},{"id":"2405.07615","title":"ViWikiFC: Fact-Checking for Vietnamese Wikipedia-Based Textual Knowledge Source","created":"2024-05-13","cited_by_count":4,"area":null},{"id":"2503.03285","title":"Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2505.23714","title":"SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2507.19995","title":"VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering","created":"2025-07-26","cited_by_count":4,"area":null},{"id":"2209.14494","title":"Multi-stage Information Retrieval for Vietnamese Legal Texts","created":"2022-09-29","cited_by_count":3,"area":null},{"id":"2405.14141","title":"ViHateT5: Enhancing Hate Speech Detection in Vietnamese With A Unified Text-to-Text Transformer Model","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2410.17532","title":"Responsible Multilingual Large Language Models: A Survey of Development, Applications, and Societal Impact","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2412.11483","title":"\"They've Stolen My GPL-Licensed Model!\": Toward Standardized and Transparent Model Licensing","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2603.05690","title":"FreeTxt-Vi: A Benchmarked Vietnamese-English Toolkit for Segmentation, Sentiment, and Summarisation","created":"2026-03-05","cited_by_count":3,"area":null},{"id":"2102.12162","title":"From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection","created":"2021-02-24","cited_by_count":2,"area":null},{"id":"2112.11052","title":"Predicting Job Titles from Job Descriptions with Multi-label Text Classification","created":"2021-12-21","cited_by_count":2,"area":null},{"id":"2112.15338","title":"Clustering Vietnamese Conversations From Facebook Page To Build Training Dataset For Chatbot","created":"2021-12-31","cited_by_count":2,"area":null},{"id":"2209.08359","title":"From Disfluency Detection to Intent Detection and Slot Filling","created":"2022-09-17","cited_by_count":2,"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":"2211.05015","title":"Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2311.12475","title":"PhayaThaiBERT: Enhancing a Pretrained Thai Language Model with Unassimilated Loanwords","created":"2023-11-21","cited_by_count":2,"area":null},{"id":"2411.17270","title":"An Attempt to Develop a Neural Parser based on Simplified Head-Driven Phrase Structure Grammar on Vietnamese","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2412.16365","title":"Overview of the First Workshop on Language Models for Low-Resource Languages (LoResLM 2025)","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2505.10945","title":"Semantic Aware Linear Transfer by Recycling Pre-trained Language Models for Cross-lingual Transfer","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2505.24229","title":"Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2110.02052","title":"Transfer Learning for Multi-lingual Tasks -- a Survey","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2110.04257","title":"VieSum: How Robust Are Transformer-based Models on Vietnamese Summarization?","created":"2021-10-08","cited_by_count":1,"area":null},{"id":"2209.11035","title":"MonoByte: A Pool of Monolingual Byte-level Language Models","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2210.14607","title":"A practical method for occupational skills detection in Vietnamese job listings","created":"2022-10-26","cited_by_count":1,"area":null},{"id":"2211.05025","title":"Local Structure Matters Most in Most Languages","created":"2022-11-09","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":"2309.05500","title":"NeCo@ALQAC 2023: Legal Domain Knowledge Acquisition for Low-Resource Languages through Data Enrichment","created":"2023-09-11","cited_by_count":1,"area":null},{"id":"2312.09000","title":"ComOM at VLSP 2023: A Dual-Stage Framework with BERTology and Unified Multi-Task Instruction Tuning Model for Vietnamese Comparative Opinion Mining","created":"2023-12-14","cited_by_count":1,"area":null},{"id":"2401.01108","title":"Unveiling Comparative Sentiments in Vietnamese Product Reviews: A Sequential Classification Framework","created":"2024-01-02","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":"2402.02655","title":"VlogQA: Task, Dataset, and Baseline Models for Vietnamese Spoken-Based Machine Reading Comprehension","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2405.02573","title":"A Combination of BERT and Transformer for Vietnamese Spelling Correction","created":"2024-05-04","cited_by_count":1,"area":null},{"id":"2405.13292","title":"Metadata Integration for Spam Reviews Detection on Vietnamese E-commerce Websites","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2406.13337","title":"Medical Spoken Named Entity Recognition","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2408.04174","title":"wav2graph: A Framework for Supervised Learning Knowledge Graph from Speech","created":"2024-08-08","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":"2411.13407","title":"Transformer-Based Contextualized Language Models Joint with Neural Networks for Natural Language Inference in Vietnamese","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2502.19202","title":"LiGT: Layout-infused Generative Transformer for Visual Question Answering on Vietnamese Receipts","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2512.13552","title":"PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generation","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2601.04711","title":"DSC2025 -- ViHallu Challenge: Detecting Hallucination in Vietnamese LLMs","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.10167","title":"Credit C-GPT: A Domain-Specialized Large Language Model for Conversational Understanding in Vietnamese Debt Collection","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2605.00116","title":"ViLegalNLI: Natural Language Inference for Vietnamese Legal Texts","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2102.10794","title":"ReINTEL Challenge 2020: Exploiting Transfer Learning Models for Reliable Intelligence Identification on Vietnamese Social Network Sites","created":"2021-02-22","cited_by_count":0,"area":null},{"id":"2102.12136","title":"Augmenting Part-of-speech Tagging with Syntactic Information for Vietnamese and Chinese","created":"2021-02-24","cited_by_count":0,"area":null},{"id":"2109.12777","title":"ReINTEL Challenge 2020: A Comparative Study of Hybrid Deep Neural Network for Reliable Intelligence Identification on Vietnamese SNSs","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2110.05896","title":"LaoPLM: Pre-trained Language Models for Lao","created":"2021-10-12","cited_by_count":0,"area":null},{"id":"2203.07742","title":"ViWOZ: A Multi-Domain Task-Oriented Dialogue Systems Dataset For Low-resource Language","created":"2022-03-15","cited_by_count":0,"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":"2301.00422","title":"Leveraging Semantic Representations Combined with Contextual Word Representations for Recognizing Textual Entailment in Vietnamese","created":"2023-01-01","cited_by_count":0,"area":null}],"next_cursor":"100"}