nlp

Implementation of TSDS: Data Selection for Task-Specific Model Finetuning. An optimal-transport framework for selecting domain-specific and task-specific training data to improve LLM finetuning and instruction tuning.

A feature-rich web application for automated news scraping and summarization. It allows users to enter article URLs, fetches the full content, and generates concise summaries. The system supports both local inference with custom models and remote deployment via FastAPI or Streamlit interfaces.

Convenient Text-to-Text Training for Transformers

KAREN: Unifying Hatespeech Detection and Benchmarking

Advanced PDF/Document Translator with interactive comparison. Built on IBM Docling.

ChatGPT, embedding search, and retrieval-augmented generation for Squeak/Smalltalk

"Solace AI: Your Empathetic Digital Confidant": Solace AI is an empathetic mental health companion that understands your emotions and personality to provide personalized support through natural conversations. It creates a judgment-free space where you can express yourself freely and receive compassionate guidance tailored just for you.

Advanced RAG (Retrieval-Augmented Generation) system for private document intelligence. Uses OpenAI GPT-4o and Vector Databases to provide zero-hallucination chat insights.

An interactive web application for comparing PDF documents using cosine similarity scans and a chatbot interface to explore and interact with PDF content.

Grounding Language Models for Compositional and Spatial Reasoning

面向小团队的一站式 NLP 小模型平台:数据集版本管理 · 训练 · 评估 · 在线部署 · Badcase 闭环,内置大模型 Prompt 盲测评测(人工 + AI 双指标)。

Finetuning a small BLOOMZ model (bloomz-560m) on a small dataset and with limited resources.

Use ESG-BERT model to classify text of sustainability reports

Sarcasm is a term that refers to the use of words to mock, irritate, or amuse someone. It is commonly used on social media. The metaphorical and creative nature of sarcasm presents a significant difficulty for sentiment analysis systems based on affective computing. The technique and results of our team, UTNLP, in the SemEval-2022 shared task 6 on sarcasm detection are presented in this paper.

This project is used to generate a blog post using Natural Language processing, Hugging Face Transformers and GPT-2 Model.

A tool for performing semantic search within pdf documents leveraging sentence transformers.

Self-hostable AI text detector, bring your own model, calibrate on your domain, run locally or on Modal GPU.

Text Summarization on Spotify Podcast Transcripts for NLP class at @UNIBO

Built a GUI application using Tkinter that helps Doctors to prepare prescriptions more efficiently. This uses speech to text conversion and text extraction to prepare prescriptions in the correct format. This project is submitted for Smart India Hackathon 2020.

Open source voice bot for Humanoid Robots and virtual digital humans