Utilities for training and evaluating text predictors based on Stupid Back-off N-gram models.

Create and adapt n-gram and JSGF language models, e.g. for Kaldi-ASR nnet3 chain models from Zamia-Speech

NLP project on Language Modelling - ENSAE ParisTech

Predictive texting is a data processed tool that makes it quicker and easier to write text by suggesting words as you type. The tool will read the text inside the text input area and predict the three most suitable options. After the prediction is made, the options are displayed as buttons. The user can press the button to insert text, the tool …

This model predicts upto 3 words that the user might use next based upon the text entered. It was built using text data from Twitter, Blogs and News. Currently, it's built for English Text and can be further used for other languages. It is made by building n-gram models (bigrams, trigrams and quadgrams).

To build a multi-class model using Sklearn-pipelines that’s capable of detecting different types of toxicity