A collection of research on knowledge graphs

Straightforward fuzzy matching, information retrieval and NLP building blocks for JavaScript.

NeuralQA: A Usable Library for Question Answering on Large Datasets with BERT

Official code for ACL2025 "🔍 Retrieval Models Aren’t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models"

Collaboration Spotting X - A network-based information retrieval and visual-analytics application

Chrome extension for creating custom Smart Replies in Gmail

This repository contains the Domain Discovery Tool (DDT) project. DDT is an interactive system that helps users explore and better understand a domain (or topic) as it is represented on the Web.

The Web IR / NLP Group (WING)'s public reading group at the National University of Singapore.

Tunable full text search engine in JavaScript that: (1) works natively on web apps like Express.js; (2) easy to customize (via BM25) to specific types of documents (e.g. tweets, scientifc journals); (3) is deployable on either the client-side or the server side.

Simple Infopanel is a free digital signage software that functions like a slider, displaying a title, image, description text, and a QR code for a URL on each page. It offers an intuitive GUI for editing, featuring a simple role-based concept. This tool is perfect for digital signage, information panels, news aggregators, events, or similar apps.

This is the main repository for the DocTAG annotation tool. DocTAG is a portable, customizable annotation tool specifically designed for the Information Retrieval (IR) domain.

👾 Project - Now getting information from your github is easy.

A module for creating stopword lists for any language, based on a set of documents.

This is the frontend layer of SearchX. SearchX is a scalable collaborative search system being developed by Lambda Lab of TU Delft.

A Model Context Protocol (MCP) compliant server designed for comprehensive web research. It uses Tavily's Search and Crawl APIs to gather detailed information on a given topic, then structures this data in a format perfect for LLMs to create high-quality markdown documents.

This is the backend layer of SearchX. SearchX is a scalable collaborative search system being developed by Lambda Lab of TU Delft.

A semantic food search web application built with Django, Solr, SBERT, and Docker

A Node.js library for keyword search and information retrieval. The library uses tf-idf cosine similarity to rank which documents in a corpus are most relevant to an input query.

Personality analysis based matchmaking. This project was made as a part of my information retrieval course.

An idiom search engine