mbert

This repository contains the official release of the model "BanglaBERT" and associated downstream finetuning code and datasets introduced in the paper titled "BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla" accpeted in Findings of the Annual Conference of the North American Chap…

Improving Word Translation via Two-Stage Contrastive Learning (ACL 2022). Keywords: Bilingual Lexicon Induction, Word Translation, Cross-Lingual Word Embeddings.

Open Text Shield (OTS) is an open-source SMS classification AI model, trained and maintained by the team at TelecomsXChange.

A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Language

An observatory of anglicism usage in the Spanish press

Official Repository for the paper titled "Meta-Learning for Effective Multi-task and Multilingual Modelling" accepted at EACL 2021

[EMNLP 2022] Discovering Language-neutral Sub-networks in Multilingual Language Models.

Your personal study assistant! This bot makes learning easier by converting YouTube videos into summarized notes with key points. Just send a video link, and get a clear PDF summary—perfect for studying, revising, or quickly understanding any topic.

This study introduces MultiBanFakeDetect, a multimodal dataset for Bangla fake news detection, combining textual and visual information. It features TextFakeNet for text analysis and MultiFusionFake for integrating multimodal data.

Zero-shot and Translation Experiments on XQuAD, MLQA and TyDiQA

mBERT and XLM-R for encodeing of Scandinavian languages

This research examines the performance of Large Language Models (GPT-3.5 Turbo and Gemini 1.5 Pro) in Bengali Natural Language Inference, comparing them with state-of-the-art models using the XNLI dataset. It explores zero-shot and few-shot scenarios to evaluate their efficacy in low-resource settings.

ICEBERT: Interlingual-Clusters Enhanced BERT. A BERT-like model trained on clusters of monolingual subwords.

ZeroShot XNLI

Abusive language detection for code-mixed Hinglish using mBERT, XLM-RoBERTa, and hybrid Transformer-BiLSTM models on 824K ShareChat comments.

Deployed model which can summarize Lithuanian language text by leveraging Artificial Neural Networks, Transformers, mBERT.

Hallucination Detection in Pretrained Generative AI Models for Bengali Text - A benchmark dataset of 7,043 annotated samples and fine-tuned transformer architectures (BanglaBERT & mBERT).

By using the hypothesis of historical linguistics, we found a way to improve the performance of multilingual transformers with limited amount of data

Online gender-based violence limits marginalized voices. Detection in Indic languages is hard due to limited data and linguistic complexity. This work builds better classifiers for improved abuse detection in such settings.