Skip to content

Latest commit

 

History

History
40 lines (24 loc) · 2.62 KB

README.md

File metadata and controls

40 lines (24 loc) · 2.62 KB
Raw

Deep Learning for NLP - Tutorial

Hands-on tutorial on deep learning with a special focus on Natural Language Processing (NLP).

This GIT repository accompanies the UKP lectures and seminars on Deep Learning for Natural Language Processing. In contrast to other tutorials, this tutorial focuses on the usage of deep learning methods.

Deep Learning for NLP - Seminar - July 2017

In July 2017 I updated the slides to the most recent Python and Keras version. The slides as well as the source code is available in the folder 2017-07_Seminar. The code in the folder can be run with either Python 2.7 or Python 3.6, with Keras 2.0.5 and with Theano (0.9.0) or TensorFlow (1.2.1) as backend.

Four different deep learning models for NLP are covered in the folder:

  1. Feed Forward Architecture for Sequence Classification (e.g. POS, NER, Chunking)
  2. Convolutional Neural Network for Sentence / Text Classification (e.g. sentiment classification)
  3. Convolutional Neural Network for Relation Extraction (e.g. semantic relation extration)
  4. Long-Short-Term-Memory (LSTM)-Networks for Sequence Classificaiton

Deep Learning for NLP - Seminar - Nov. 2016

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:

  1. Feed Forward Architecture for Sequence Classification (e.g. POS, NER, Chunking)
  2. Convolutional Neural Network for Sentence / Text Classification (e.g. sentiment classification)
  3. Convolutional Neural Network for Relation Extraction (e.g. semantic relation extration)
  4. Long-Short-Term-Memory (LSTM)-Networks for Sequence Classificaiton

Deep Learning for NLP - Lecture - Oct. 2015

In October 2015 I gave a lecture for the UKP Department at the Technical University of Darmstadt. The lecture is structured in six parts and covers the basics about deep learning. In the lecture I use Python 2.7, Theano 0.6.0 and Keras 0.3.0 to model different applications of deep learning for NLP. The slides, the source code, and video recordings are available in the folder 2015-10_Lecture.

Contact

Contact person: Nils Reimers, reimers@ukp.informatik.tu-darmstadt.de

http://www.ukp.tu-darmstadt.de/

http://www.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.