Chris Hokamp's repositories
zero-shot-ner-fine-tuning
zero shot NER fine tuning
dynamic-transformer-ensembles
Dynamic ensemble decoding with transformer-based models
aylien-datascience-demos
a collection of open-source data science demos built on top of the Aylien NewsAPI.
OpenNMT-py
Open Source Neural Machine Translation in PyTorch
dbpedia-spotlight-model
Improving Efficiency and Accuracy in Multilingual Entity Extraction approach
extraction-framework
The software used to extract structured data from Wikipedia
pytorch-pretrained-BERT
PyTorch version of Google AI's BERT model with script to load Google's pre-trained models
qe_sequence_labeling
APE-QE stuff with a word level QE server
constrained_decoding
Lexically constrained decoding for sequence generation using Grid Beam Search
neural_imt
Our implementation of Neural Interactive Machine translation, created for research
wikistatsextractor
A small tool made to extract statistics from Wikipedia Dump files.
annotated-transformer
http://nlp.seas.harvard.edu/2018/04/03/attention.html
model-quickstarter
Tools and data for creating DBpedia Spotlight models.
subword-nmt
Subword Neural Machine Translation
node-xliff
some simple utilities for creating XLIFF files from text
pyahocorasick
Python module (C extension and plain python) implementing Aho-Corasick algorithm
multimodal_nmt
Multimodal Neural Machine Translation with Minimum Risk training objectives
blocks-extras
A collection of extensions to the Blocks framework