Efficient and Scalable Estimation of Tool Representations in Vector Space

Finetuning the DeBERTa v3 model for the emotion recognition task

Detect or classify input sentences as grammatically correct or incorrect by fine-tuning pre-trained DeBERTa-v3 model

Application for training the pretrained transformer model DeBERTaV3 on an Aspect Based Sentiment Analysis task

Official repository for the EMNLP 2024 paper "How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics"

Finding the source code hidden in the text.

Submodular Subset Selection for Long-Document Question Answering

Backbone: 5 x DeBerta and Head: Rapids SVR

This repo details code for building a text classifier for predicting Bank Transaction categories. I finetune a base version of a DeBERTaV3 model purely on text data, as well as another version using a combination of text and non-text (e.g., categorical, datetime, etc.) data.

My pipeline for the Feedback Prize - Predicting Effective Arguments competition on Kaggle

Teknofest 2023 Doğal Dil İşleme Yarışması

Tools for DataScience and AI

ViBERTa is a fine-tuned DeBERTa model for sentiment analysis of McDonald's customer reviews, classifying sentiments as positive, negative, or neutral.

GPT 3.5 FineTuning

NLP + Finetuning + Feature Engi

Topic Modelling, Text Summarization, and Aspect-Based Sentiment Analysis (ABSA) of BBC News with transformers and LLMs. Data are fetched from BigQuery with SQL

Confidential NLP Email Classification using Multi-Party Computation

PII detection in student essays