Machine Learning tutorials with TensorFlow 2 and Keras in Python (Jupyter notebooks included) - (LSTMs, Hyperameter tuning, Data preprocessing, Bias-variance tradeoff, Anomaly Detection, Autoencoders, Time Series Forecasting, Object Detection, Sentiment Analysis, Intent Recognition with BERT)

Rhasspy voice assistant for offline home automation

TEXTOIR is the first opensource toolkit for text open intent recognition. (ACL 2021)

[RA-L20] Long-Term Pedestrian Trajectory Prediction Using Mutable Intention Filter and Warp LSTM

Open source intent recognition framework powered by LLMs.

This repository is a comprehensive project that leverages the XLM-Roberta model for intent detection. This repository is a valuable resource for developers looking to build and fine-tune intent detection models based on state-of-the-art techniques.

ChatAssist Pro is an advanced AI-powered chatbot designed to streamline customer support interactions.

DropSuit - NLP & data manipulation library for JS & Node.js. Offers diverse functions for text analysis, language understanding & more. Open-source under Apache License 2.0.

Interactive NLP-based AI system designed to manage cinema bookings and provide a seamless user experience.

Constructing a dialogue chat bot, which will be able to: answer programming-related questions (using StackOverflow dataset); chit-chat and simulate dialogue on all non programming-related questions.

Research on the Construction Method of Intelligent Services Based on Prior Knowledge

Python library to extract intention and structured information from sentences written in natural language

Powered by langgraph, a voice-enabled chatbot system capable of handling multiple analysis tasks in parallel through intent detection.

Constructing a corpus of ancient Chinese pediatric medicine literature, using algorithms such as BERT, lattice LSTM, and Siamese for tasks such as named entity recognition, intent recognition, entity similarity calculation, and entity linking, to develop a TCM-QA.

English Intention Annotation Data

Project for my Conversational Agents course at UNITN.

The qaio function is a JavaScript and Node.js function that is part of the DropSuit NLP library. It is designed for response search by processing input strings or constructor input, with options of return type. Open-source and available under the Apache License 2.0.

A voice-operated emailing mobile application that allows you to compose and send email messages through voice commands.

The capability of an AI model (here, ChatGPT in particular) was tested in the sphere of customer service by availing data from real customers who had recently had experiences dealing with the chatbots or any other language model of an established institute or company.

Practical from my Social Signal Processing class