Reuters-21578 multi-class multi-label Classification with Keras

Boolean retrieval search engine with SPIMI indexing and BM25 ranking

This code is based on an unfinished paper of mine that uses a version of topological sorting and WordNet to perform extraction based summarization of a corpus.

Github Repo for CSE 573 project : Document Clustering and 3D Visualization

Java parser for the "Reuters-21578, Distribution 1.0" Text Categorization data set.

Named Entity Recognition (NER) using Conditional Random Field (CRF) in Python

Learning NLP Through Data

This Introduction to Deep Learning course project is about topic classification on the Reuters corpus. Tecs: python - jupyter notebook - deep learning - pytorch - huggingface - transformer - BERT

🎙 HW4 of Intelligent Information Retrieval MSc Course ECE@UT

A C++ library for boolean search using a positional inverted index on Reuters-21578 dataset.

Document Retrieval System / Simple Text Retrieval System, for the Reuters-21578 dataset [SGM -> XML -> Text File]

Reuters 1987 Corpus Topic classification

Reuters-21578 Corpus is a collection of documents consisting of news articles which appeared on Reuters newswire in 1987. The corpus is available in NLTK package in Python. Topic Modelling has been conducted on this Reuters-21578 corpus of news documents using Latent Dirichlet Allocation (LDA). The obtained topics have been visualized using prop…

This project is for the Helsinki University Interactive data visualization course

Spimi implementation in php using reuters corpus. For course Comp479