AI and Memory Wall

Resources for the paper: Monolingual Pre-trained Language Models for Tigrinya

A module that combines the power of Reformer/FastFormer, Electra and memory efficient compositional embeddings

BioMedical Language Processing with ELECTRA

Electra model for (Extractive) Question Answering on Italian texts

This project focuses on utilizing natural language processing (NLP) techniques to address the critical issue of suicide prevention. By leveraging advanced NLP models like BERT and ELECTRA, we aim to analyze linguistic patterns indicative of suicidal ideation.

[EMNLP 2024 Findings] Are ELECTRA's Sentence Embeddings Beyond Repair? The Case of Semantic Textual Similarity