Collection of tools for building diachronic/historical word vectors

Practice how to perform text classification using a machine learning classification model and combinations of word embeddings or sentence embeddingsas a feature vector

About App to compare state-of-the-art models for semantic clustering task

A model-based cleaner using Laser sentence embeddings to exploit embeddings to filter misaligned segment pairs. Product scaled by asynchronously building the Task Queues, dispatching the tasks in a Round Robin method and adding multiple workers on the RabbitMQ server for consumption.

Dashboard showing map and graphs for the UCF Crimes Database (February to August). Filters over location and titles (similarity search)

a bookmarking tool with useful features such as auto tagging and more!

RAG-based Streamlit app that uses Langchain, OpenAI Embeddings, GPT, and Pinecone Vector Database to answer questions about a user-provided document

A repository to host the files used and developed during the master thesis period.

A novel system for the automated question & answering of product-related user queries present on e-commerce websites using Capsule Networks (implemented in Keras)

Data and code for the paper "Inferring multilingual domain-specific word embeddings from large document corpora"

A BERT-inspired machine learning architecture for understanding contextual agent roles in team compositions in VALORANT

Embedding API server using Sequence Transformers

Facts are all you need! Blog without writing, blog with just facts.

Chatbot para inteactuar con PDF usando LangChain y OpenAI / HuggingFace

using langchain agent and react framework

AI chat assistant for a specific codebase by retreiving relevant details using rag and chroma db

Learning Embeddings with Multiple Linguistic Fields @NAACL2021

This course examines the theoretical and applied problems of constructing and modelling systems, which aim to extract and represent the meaning of natural language sentences or of whole discourses, but drawing on contributions from the fields of linguistics, cognitive psychology, artificial intelligence and computing science.

Code for generating word2vec embeddings for the Romanian language, and some precomputed embeddings.