language-modelling

PyNLPl, pronounced as 'pineapple', is a Python library for Natural Language Processing. It contains various modules useful for common, and less common, NLP tasks. PyNLPl can be used for basic tasks such as the extraction of n-grams and frequency lists, and to build simple language model. There are also more complex data types and algorithms. Moreover, there are parsers for file formats common in NLP (e.g. FoLiA/Giza/Moses/ARPA/Timbl/CQL). There are also clients to interface with various NLP specific servers. PyNLPl most notably features a very extensive library for working with FoLiA XML (Format for Linguistic Annotation).

Contextualised Embeddings and Language Modelling using BERT and Friends using R

Transformer Based SeqGAN for Language Generation

Code for my master thesis in Deep Learning: "Generating answers to medical questions using recurrent neural networks"

Pytorch implementation of MaskGAN

Language Modelling, CMI vs Perplexity

PyTorch implementations of word embeddings and language modelling.

Memory Based Word Predictor/Language Model http://ilk.uvt.nl/wopr/

Spelling correction and grammar detection with statistical language models

This repository contains code and data download instructions for the workshop paper "Improving Hierarchical Product Classification using Domain-specific Language Modelling" by Alexander Brinkmann and Christian Bizer.

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.

Various Deep Learning concepts implemented using TensorFlow

State-of-the-Art Language Modelling in Python with PyTorch.

A simple series of programs to train gated recurrent neural networks with PyTorch and generate text based on them.

In this project we will generate the sentences using ngrams

Transformer and GPT Network Codes using both Tensorflow and PyTorch.

Decoder model for language modelling

Sequence CNN network inspired by the WaveNet architecture written in both Tensorflow and PyTorch.

Reproduction of CIFAR-10/CIFAR-100 and Penn Treebank experiments to test claims in "LookaheadOptimizer: k steps forward, 1 step back" https://arxiv.org/abs/1907.08610

This code project is associated with my master thesis (at the company Omicron Ceti AB) that I have done during spring 2019 at Royal Institute of Technology. The report, to which the code project is associated, is included in this Github repository as "report.pdf".

Natural Language Processing topics and projects.

Introduce basic nlp tasks and methods with examples

An Implementation One of Natural Language Processing Method : Language Modelling

Reproduction of CIFAR-10/CIFAR-100 and Penn Treebank experiments to test claims in "LookaheadOptimizer: k steps forward, 1 step back" https://arxiv.org/abs/1907.08610