text_mining

To see the main results I highily recommend to take a look at the project page: https://schalkdaniel.github.io/text_mining/

Purpose

This repo contains everything I have used, created or take a look at for the .

My topic for the seminar is: GloVe

This repository conatins:

• ioslides for the presentation
• code which I have written (C++ and R)
• paper and references I have used
• the report written by me

References

• Pennington et al.
• Mirkov et al.
• Aggarwal et al.
• Grammar & Corpora 2009
• text2vec

ToDos

• write the report

Topics

1. A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques.
2. Classification methods (book "Elements of Statistical Learning" of Hastie et al.). Kapitel 4.
3. Support Vector Machine (ESL, Kapitel 12).
4. Unsupervised Learning (ESL, Kapitel 14).
5. Natural Language Basics (Chapter 1 of Dipanjan).
6. Python Refresher (Chapter 2 of Dipanjan).
7. Processing and understanding text (Chapter 3 of Dipnajan).
8. Text classification (Chapter 4 of Dipanjan).
9. Text summarization (Chapter 5 of Dipanjan).
10. Text similarity and text clustering (Chapter 6 of Dipanjan).
11. Semantic and Sentiment Analysis (Chapter 7 of Dipanjan).
12. GloVe: Global Vectors for Word Representation (Pennington et al.)
13. Distributed representations of words and phrases and their compositionality (Mikolov et al.)
14. Distributed representations of sentences and documents (Le et al.)
15. Convolutional Neural Networks for Sentence Classification (Yoon Kim).
16. Text Understanding from Scratch (Zhang, LeCun).
17. Generative Adversarial Text to Image Synthesis (Reed et al.).