perplexity

Python implementation of an N-gram language model with Laplace smoothing and sentence generation.

评估自然语言的流畅度

Programming for NLP Project - Implement a basic n-gram language model and generate sentence using beam search

Language Modelling, CMI vs Perplexity

Automatic Response Generation to Conversational Stimuli

Protests and agitations have long used as means for showing dissident towards social, political and economic issues in civil societies. In recent years we have witnessed a large number of protests across various geographies. Not to be left behind by similar trends in the rest of the world, South Africa, in recent years have witnessed a large number of protests. This paper uses the English text description of the protests to predict their time spans/durations. The descriptions consist of multiple causes of the protests, courses of actions etc. Next we used unsupervised (topic modeling) and supervised learning (decision trees) to predict the duration of protests. The results are very promising and close to 90% of accuracy in early predicting of the duration of protests.

Online Essay Grading system using Django Frwamework, NLP, NLTK, Keras and many more.

Generating text sequences using attention-based Bi-LSTM

demo of domain corpus bootstrapping using language model perplexity

NLP project on Language Modelling - ENSAE ParisTech

Bigram and Trigram Language Models. This repository provides my solution for the 1st Assignment for the course of Text Analytics for the MSc in Data Science at Athens University of Economics and Business.

This repository consists of comparison between two LDA algorithms (EM and Online) in Apache Spark 'mllib' library and also finding the best hyper parameters on YELP dataset.

In this project we will generate the sentences using ngrams

N-gram Language Model

You will learn to implement t-SNE models in scikit-learn and explain the limitations of t-SNE. Being able to abstract high-dimensional information into lower dimensions will prove helpful for visualization and exploratory analysis, as well as in conjunction with the clustering algorithms. By the end of this course, you will be able to find clusters in high-dimensional data, such as user-level information or images.

Code for paper: "Numeracy Enhances the Literacy of Language Models"

Predicting the next word using n-grams

MNIST Digit recognition using machine learning techniques

Practical demonstration of scikit learn library for building various classification and regression models

statistical natural language processing with n-gram,Smoothing,Perplexity.

Word-prediction algorithm implemented in R (with R Shiny app) then redone in a simplified Python version

The autocomplete system model for Indonesian was built using the perplexity score approach and n-grams count probability in determining the next word.

This program uses diphone (bigram) and triphone (trigram) models to represent Mainstream American English (MAE) phonotactics.

language modeling

Django Application linked to PHP

language modeling, bigram, trigram, mixture of language models, perplexity, Gutenberg project