Bidirectional Encoder Representations from Transformers

Also known as BERT

Latest papers

10 papers0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

NEPSEE: A Double-Annotated Benchmark for Nepali Sentiment Analysis
Oct 13, 2026Gaurab Baral, Mimansak Nepal, Grishma BasnetSentiment Analysis LLM Evaluation
University of Cincinnati Cincinnati, Ohio, USA · Tribhuvan University Kirtipur, Kathmandu, Nepal · Subhakamana English School Urlabari, Morang, Nepal
Automated Multilabel Mpox Research Classification with Explainable Transformer Models
Jul 29, 2026Tanjim Taharat AurpaExplainable Text Classification Multi-Label Classification
Department of Data Science and Engineering, University of Frontier Technology, Bangladesh (UFTB)
Comparative Analysis of GAT and BERT for Human-Like Playtesting
Jul 13, 2026Kleio Fragkedaki, Theodoros Panagiotakopoulos, Matteo Biasielli +1Graph Attention Networks Graph Neural Networks
AI Center of Excellence King Stockholm, Sweden
Multi-Class vs. Multi-Label BERT for CVE-to-CWE Mapping: How Taxonomy Structure Shapes the Errors
Jul 8, 2026Ana Schwengber Kelm, Christian Bockermann, Jörg FrochteHierarchical Classification Multi-Label Classification
mindsquare AG · Bochum University of Applied Sciences
Legal Domain Adaptation of Modern BERT Models
Jun 26, 2026Dominik Stammbach, Peter HendersonLegal NLP Bidirectional Encoder Representations from Transformers
Princeton University Princeton, New Jersey, USA
Continuous Behavioral Authentication via Multi-Expert BERT Log Analysis for Secure Data Sharing
Jun 20, 2026Stergios Lantzos, Ilias Syrigos, Apostolos Apostolaras +1Bidirectional Encoder Representations from Transformers Anomaly Detection
Dept. of Electrical and Computer Engineering, University of Thessaly, Greece
NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data
Apr 12, 2026Cong Ming, Ruixin Shi, Yifan HuBidirectional Encoder Representations from Transformers Large Language Model-Based Data Augmentation
Northeastern University, United States
Detecting Toxic Language: Ontology and BERT-based Approaches for Bulgarian Text
Apr 2, 2026Melania Berbatova, Tsvetoslav VasevBidirectional Encoder Representations from Transformers Toxicity Detection
Faculty of Mathematics and Informatics, Sofia University "St. Kliment Ohridski"
PersianPunc: A Large-Scale Dataset and BERT-Based Approach for Persian Punctuation Restoration
Mar 5, 2026Mohammad Javad Ranjbar Kalahroodi, Heshaam Faili, Azadeh ShakeryBidirectional Encoder Representations from Transformers Low-Resource Language Processing
University of Tehran, Tehran, Iran · Institute for Research in Fundamental Sciences (IPM), Tehran, Iran
Benchmarking BERT-based Models for Sentence-level Topic Classification in Nepali Language
Feb 27, 2026Nischal Karki, Bipesh Subedi, Prakash Poudyal +2Bidirectional Encoder Representations from Transformers Text Classification
Information and Language Processing Research Lab, Kathmandu University, Kavre, Nepal

Oct 13, 2026J/K move · Enter open · S save

NEPSEE: A Double-Annotated Benchmark for Nepali Sentiment Analysis

Gaurab Baral, Mimansak Nepal, Grishma Basnet

University of Cincinnati Cincinnati, Ohio, USA · Tribhuvan University Kirtipur, Kathmandu, Nepal · Subhakamana English School Urlabari, Morang, Nepal

Sentiment Analysis LLM Evaluation Bidirectional Encoder Representations from Transformers

Open paper AskPDF arXiv

Many sentiment datasets use one annotator for each item, so the test labels show the conventions of that person. We build a Nepali benchmark from two annotators who labelled the same sentences blind. They labelled 5,614 sentences from tweets of Nepali public figures on a five-point scale. We keep only the 3,189 sentences where both give the same polarity. On the three-class benchmark, NepBERTa with a fixed tokenizer gets a macro-F1 of 0.877 and IndicBERTv2 0.867. Three commercial large language models (LLMs) get 0.882 to 0.896 zero-shot, and these differences are not significant. On the five-point scale, 766 sentences have two adjacent labels, for example Pos and SPos. We accept both labels and train on both. On this task, Claude Opus 5.5 beats the best encoders by 0.10 to 0.12 macro-F1. A tokenizer audit adds a second result. The default tokenizers of three Nepali BERT models delete the non-spacing Devanagari vowel signs and the virama. When we restore the marks, macro-F1 increases by 0.084 for NepBERTa but decreases by 0.095 for a model pretrained on stripped text.