fredriko

bert-tensorflow-pytorch-spacy-conversion

Instructions for how to convert a BERT Tensorflow model to work with HuggingFace's pytorch-transformers, and spaCy. This walk-through uses DeepPavlov's RuBERT as example.

nlp-data-readiness

This is a document concerning Data Readiness in the context of machine learning and Natural Language Processing.

metacurate-lexicon

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

gavagai-lexicon-graph

Creates a Neo4j graph database from Gavagai Living Lexicon entries

draviz

A method for assessing the data readiness of NLP projects, as well as the code necessary for visualizing the outcome of the method.

debiaswe

Remove problematic gender bias from word embeddings.

facebook-page-retriever

Utility for downloading posts from Facebook Pages and save them as CSV

graphipedia

Creates a Neo4j graph of Wikipedia links.

metacurate-regularly

Finding the top news stories of 2022 among 54,000+ news on AI, ML, NLP, data science and related fields.

bestbuy-reviews-retriever

Utility for downloading product reviews from BestBuy

data-centric-deep-learning

Public repository for the "Data-Centric Deep Learning" course taught by Mike Wu and Andrew Maas. Available at https://corise.com/course/data-centric-deep-learning.

daypart

deep-text-classification-pytorch

Deep neural network text classification papers in PyTorch

fast-bert

Super easy library for BERT based NLP models

fredriko.github.io

Fredrik Olsson, personal web page

full-stack-ml-metaflow-corise-week-1

full-stack-ml-metaflow-corise-week-2

full-stack-ml-metaflow-corise-week-3

full-stack-ml-metaflow-corise-week-4

gnip4j

Gnip Client Library for Java

graph2vec

A parallel implementation of "graph2vec: Learning Distributed Representations of Graphs" (MLGWorkshop 2017).

metacurate.io

morphological_expander

A Python wrapper to mophologically expand terms using the UniMorph knowledge base. Lemmatises the input term and re-inflects the lemma to all possible surface forms.

pytorch-transformers

👾 A library of state-of-the-art pretrained models for Natural Language Processing (NLP)

russian-troll-tweets

scholarly

Retrieve author and publication information from Google Scholar in a friendly, Pythonic way

search_with_machine_learning_course

Public repository for the Search with Machine Learning course taught by Daniel Tunkelang and Grant Ingersoll. Available at https://corise.com/?utm_source=daniel.

sentence-transformers

Sentence Embeddings with BERT & XLNet

tweet-stance-prediction

Applying NLP transfer learning techniques to predict Tweet stance

twitter4j

Twitter4J is an open-sourced, mavenized and Google App Engine safe Java library for the Twitter API which is released under the Apache License 2.0.