Heavily trimmed version of the Deep Learning for NLP tutorial series, only including code for the RelationCNN model presented in the Nov. 2016 seminar (see description below)
In November 2016 I gave a seminar at the University of Duisburg-Essen. The slides as well as the source code is available in the folder 2016-11_Seminar. In the seminar I use Python 2.7, Theano 0.8.2, and Keras 1.1.1 to model four different deep learning models for NLP:
- Feed Forward Architecture for Sequence Classification (e.g. POS, NER, Chunking)
- Convolutional Neural Network for Sentence / Text Classification (e.g. sentiment classification)
- Convolutional Neural Network for Relation Extraction (e.g. semantic relation extration)
- Long-Short-Term-Memory (LSTM)-Networks for Sequence Classificaiton
Contact person (for original model): Nils Reimers, reimers@ukp.informatik.tu-darmstadt.de
http://www.ukp.tu-darmstadt.de/
Don't hesitate to send us an e-mail or report an issue, if something is broken (and it shouldn't be) or if you have further questions.
This repository contains experimental software and is published for the sole purpose of supporting the lectures.