chrishokamp

constrained_decoding

Lexically constrained decoding for sequence generation using Grid Beam Search

dynamic-transformer-ensembles

Dynamic ensemble decoding with transformer-based models

handycat

the flexible CAT tool

node-xliff

some simple utilities for creating XLIFF files from text

multimodal_nmt

Multimodal Neural Machine Translation with Minimum Risk training objectives

neural_mt

Neural Machine Translation based on Blocks and Fuel

qe_sequence_labeling

APE-QE stuff with a word level QE server

zero-shot-ner-fine-tuning

zero shot NER fine tuning

pybktree

Python BK-tree data structure to allow fast querying of "close" matches

annotated-transformer

http://nlp.seas.harvard.edu/2018/04/03/attention.html

aylien-datascience-demos

a collection of open-source data science demos built on top of the Aylien NewsAPI.

blocks

A Theano framework for building and training neural networks

blocks-extras

A collection of extensions to the Blocks framework

clusim

An extended package for clustering similarity

dbpedia-spotlight-model

Improving Efficiency and Accuracy in Multilingual Entity Extraction approach

elasticsearch-playground

extraction-framework

The software used to extract structured data from Wikipedia

fastbook

The fastai book, published as Jupyter Notebooks

flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

model-quickstarter

Tools and data for creating DBpedia Spotlight models.

MUSE

A library for Multilingual Unsupervised or Supervised word Embeddings

neural_imt

Our implementation of Neural Interactive Machine translation, created for research

OpenNMT-py

Open Source Neural Machine Translation in PyTorch

phrasal

A large-scale statistical machine translation system written in Java.

pyahocorasick

Python module (C extension and plain python) implementing Aho-Corasick algorithm

pytorch-pretrained-BERT

PyTorch version of Google AI's BERT model with script to load Google's pre-trained models

subword-nmt

Subword Neural Machine Translation

wcep-mds-dataset

wiki2vec

Generating Vectors for DBpedia Entities via Word2Vec and Wikipedia Dumps. Questions? https://gitter.im/idio-opensource/Lobby

wikistatsextractor

A small tool made to extract statistics from Wikipedia Dump files.