เป็นการรวบรวมแหล่งข้อมูลสำหรับการเรียนรู้เกี่ยวกับปัญญาประดิษฐ์ (Artificial Intelligence - AI) และโมเดลภาษาขนาดใหญ่ (Large Language Models - LLMs) รวมถึงหัวข้อพื้นฐาน, สมุดบันทึกที่แนะนำ, คอร์สออนไลน์, เครื่องมือ, ชุดข้อมูล และเทคนิคขั้นสูงสำหรับการพัฒนาและปรับแต่งโมเดล AI

It's Smart-Question Answering System on short as well as long documents. It can automatically find answers to matching questions directly from documents. The deep learning language model converts the questions and documents to semantic vectors to find the matching answer.

❓Fine-tuning BERT for extractive QA on SQuAD 2.0

No description provided.

Successfully developed a resume classification model which can accurately classify the resume of any person into its corresponding job with a tremendously high accuracy of more than 99%.

WSD for Word-in-Context (WiC) disambiguation, experimenting with BERT feature-based and fine-tuning approaches (GlossBERT)

Turkish Hate Speech Detection

Successfully developed a fine-tuned BERT transformer model which can effectively perform emotion classification on any given piece of texts to identify a suitable human emotion based on semantic meaning of the text.

Initially implement Document-Retrieval-System with SBERT embeddings and evaluate it in CORD-19 dataset. Afterwards, fine tune BERT model with SQuAD.v2 dataset so as to evaluate it in Question Answering task.

A comprehensive guide for beginners looking to start fine-tuning BERT models for sentiment analysis on Arabic text. This project walks through the complete process of data preprocessing, model training, and evaluation, providing a beginner-friendly tutorial on how to fine-tune and deploy machine learning models for real-world applications.

Using BERT models to perform sentiment analysis on women's clothing

External Knowledge Infusion using INCIDecoder into BERT for Chemical Mapping

Successfully developed a resume classification model which can accurately classify the resume of any person into its corresponding job with a tremendously high accuracy of more than 99%.

Successfully developed a text classification model to predict whether a given news text is fake or not by fine-tuning a pretrained BERT transformed model imported from Hugging Face.

Successfully developed a news category classification model using fine-tuned BERT which can accurately classify any news text into its respective category i.e. Politics, Business, Technology and Entertainment.

A PyTorch Lightning Implementation of Multi-Language Identification using a SentenceTransformer model pre-trained on English. Work done while interning at ByteFuse.

Question Answering with a Fine-Tuned BERT

Fine tuned BERT model for semantic analysis

No description provided.

Final project for class Data Mining and Text Mining; University of Illinois at Chicago (Fall 2023); 1st year of Master's Degree in Computer Science coursework.

UC3M "Tratamiento de Datos" Lab Project

Successfully established a Seq2Seq with attention model which can perform English to Spanish language translation up to an accuracy of almost 97%.

Notebooks for fine-tuning and evaluating pre-trained BERT models to tasks for semantic search in Web API documentation

Notebooks for fine-tuning and evaluating a pre-trained BERT model to the task of semantic parameter matching in Web APIs

Health Progress Prediction and Goal Attainment Analysis in Patient Discharge Summaries with BERT and Tensorflow. - Feb 2022 - Jun 2023

Estudio del carácter patogénico de variantes humanas mediante deep learning. Fine-tuning de BERT para la representación de enfermedades: un método de aprendizaje sobre datasets de textos biomédicos.

Successfully developed a multiclass text classification model by fine-tuning pretrained DistilBERT transformer model to classify various distinct types of luxury apparels into their respective categories i.e. pants, accessories, underwear, shoes, etc.