This repo is the official megengine implementation of the ECCV2022 paper: Efficient One Pass Self-distillation with Zipf's Label Smoothing.

Confirming that Zipf's Law is real and amazing

Paper about the generation of random numbers distributed according to the Zipf-Mandelbrot law

An experiment to demonstrate the biases and predictability of our world.

An experimental implementation of text prediction using Zipf's law to understand fundamental linguistic patterns that underlie modern language models.

Persian Search Engine, Project of Information Retrieval Course

This package implements the threshold algorithm for decimation and collapsing of time series. If use, please cite: "Torre, I. G., Luque, B., Lacasa, L., Luque, J., & Hernández-Fernández, A. (2017). Emergence of linguistic laws in human voice. Scientific reports, 7, 43862."

Implementation of unigram/bigram language models, noisy channel and pointwise mutual information for natural language processing.

Reimplementation of Manin (2008)'s models of lexical-semantic evolution

Investigating Natural Language Processing from a genomic/metagenomic perspective

Zipf Graph of a given text file

Demonstrate Zipf's law with Sherlock Holmes' stories

Discover a clever strategy for mastering Wordle! Our project dives into various Information Retrieval techniques to efficiently guess the daily word—all aiming for Wordle domination!

A coursework-style project from my MSc Machine Learning on Big Data (University of East London), using PySpark to compute word frequency distributions on a large English corpus (~9.5 million words) and to compare frequency estimates from small samples against the full dataset.

Frecuencia de palabras en las novelas "Hijo de ladrón" y "Cien años de soledad".

Demostrating Zipf's Law with Python Code

This is a simple graphical representation of Zipf's Law using term frequencies, calculated for three different text data.

Some useful NLP tools and their implementations.

A toolkit to examine Laws of Bibliometrics based on bibliometric data

🔍 A Persian-language search engine implementing Boolean and vector space models with TF-IDF ranking, supporting advanced query features like phrase search and negation.