Python Set subclass that supports searching by ngram similarity

To evaluate machine translation, they use several methods, some of which we fully implemented

This project is an auto-filling text program implemented in Python using N-gram models. The program suggests the next word based on the input given by the user. It utilizes N-gram models, specifically Trigrams and Bigrams, to generate predictions.

Use different orders of N-gram model to play Hangman game.

Part-of-Speech Tagging Models in Python

A web service that exposes semantic similarity search via a web GUI and a RESTful API.

SMP_ETST 2018 christmas

🏰 Mapping British place names and other analysis

Python implementation of N-gram Models, Log linear and Neural Linear Models, Back-propagation and Self-Attention, HMM, PCFG, CRF, EM, VAE

AdWords Script:-Find Your Best And Worst Search Queries Using N-Grams Python Version

N-Gram language model that learns n-gram probabilities from a given corpus and generates new sentences from it based on the conditional probabilities from the generated words and phrases.

ngram-keylogger: typing stats that don't leak passwords

Personality plays a vital role in todays world.This uses the Twitter REST API to mine tweets for personality identification. We will use n-grams and word vectors for the hashtags, emoticons and phrases using NLP techniques. We will train the machine to classify the personality types by using a Naive- Bayes Text Classifier and to accurately predi…

Program that encrypts plaintext and (attempts) to decrypt ciphertexts, encrypted via a mono-alphabetic substitution cipher. Replaces letters based on frequency / n-gram analysis. Tried to incorporate hill-climbing algorithm by measuring the fitness of resulting texts to find the best key.

Rediscover your past months and years using Google search data. Google allows users to download their Google data, including their search history. This project analyzes the data and creates a personalized word-cloud poster, which brings back your thoughts, fears and dreams from that period.

The code is a collection of NLP analyses, including text cleaning, most common words, n-grams generation, co-occurrence matrix generation, wordcloud generation, topic modeling (using Latent Dirichlet Allocation), and general text statistics.

Application to find the similarity score between two texts.

Simple script with a GUI that generates pronounceable passwords and places them on the clipboard.