Mark Neumann's Projects
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Generative Flow based Sequence-to-Sequence Toolkit written in Python.
Take 3 on inference for Indian Buffet Processes
Code for the UCL Information Retrieval and Data Mining Group Assignment on Models of Memory for Time Series Analysis. Mark N, Zheng T, Alexander C.
Joint Bootstrapping Machines for High Confidence Relation Extraction : NAACL-HLT 2018 Long Paper.
Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano or TensorFlow.
Python bindings for llama.cpp
Models built with TensorFlow
โจFast Coreference Resolution in spaCy with Neural Networks
Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.
QA over MatSci patents with GPT-5, with a focus on synthesis. Part of the LLM March Madness Hackathon.
Probabilistic Neural Programming
A Probabilistic U-Net for segmentation of ambiguous images implemented in PyTorch
A U-Net combined with a variational auto-encoder that is able to learn conditional distributions over semantic segmentations.
๐๐ฏpySBD (Python Sentence Boundary Disambiguation) is a rule-based sentence boundary detection that works out-of-the-box.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
Google Scholar is a trans-exclusionary site. Don't use it. Help us demand change.
This repository contains custom pipes and models related to using spaCy for scientific documents.
๐ซ Industrial-strength Natural Language Processing (NLP) with Python and Cython
A visualisation tool for Spacy using Hierplane.
Python CLI utility and library for manipulating SQLite databases
Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)