Amir-Entezari/IR-document-ranking
An information retrieval system for document ranking. Implementation and evaluation of Okapi BM25, Cosine Similarity, and Language Models for document ranking and retrieval. Includes precision-recall evaluation metrics and a detailed project report.
This project helps information architects, researchers, or anyone managing large text collections to effectively find relevant documents. You input a collection of text documents and specific queries, and it outputs a ranked list of documents most relevant to each query. This is designed for practitioners who need to optimize document search and retrieval within their systems.
No commits in the last 6 months.
Use this if you need to build or evaluate a system that retrieves the most relevant text documents in response to a user's query.
Not ideal if you are looking for a pre-built search engine with a user interface, or if your data is not primarily text-based.
Stars
5
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Jun 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Amir-Entezari/IR-document-ranking"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
williamscott701/Information-Retrieval
Information Retrieval algorithms developed in python. To follow the blog posts, click on the link:
microsoft/SimXNS
SimXNS is a research project for information retrieval. This repo contains official...
park1997/Industrial_systems_Engineering_PJ_Cloud
나홀로 소송을 준비하는 일반인을 위한 법률 정보 시스템 구축
danakianfar/information_retrieval_1
Information Retrieval Course 2017 - MSc Artificial Intelligence @ UvA
ronaldseoh/cs276
Me working on "CS276: Information Retrieval and Web Search"