Added datasets

kitsiosk · Jul 5, 2021 · 53f02a2 · 53f02a2
1 parent ee599d5
commit 53f02a2
Show file tree

Hide file tree

Showing 14 changed files with 127,149 additions and 2,584 deletions.
diff --git a/5AbastractsEvaluation.ipynb → ...sGroupDataset/5AbastractsEvaluation.ipynb b/5AbastractsEvaluation.ipynb → ...sGroupDataset/5AbastractsEvaluation.ipynb
diff --git a/5AbstractsGroupDataset/5AbstractsDataset_sgtsnepi.mat b/5AbstractsGroupDataset/5AbstractsDataset_sgtsnepi.mat
diff --git a/5AbstractsGroupDataset/Business.txt b/5AbstractsGroupDataset/Business.txt
diff --git a/5AbstractsGroupDataset/CSAI.txt b/5AbstractsGroupDataset/CSAI.txt
diff --git a/5AbstractsGroupDataset/Law.txt b/5AbstractsGroupDataset/Law.txt
diff --git a/5AbstractsGroupDataset/Sociology.txt b/5AbstractsGroupDataset/Sociology.txt
diff --git a/5AbstractsGroupDataset/Trans.txt b/5AbstractsGroupDataset/Trans.txt
diff --git a/AGNewsDataset/AGNewsData_sgtsnepi.mat b/AGNewsDataset/AGNewsData_sgtsnepi.mat
diff --git a/AGNewsEvaluation.ipynb → AGNewsDataset/AGNewsEvaluation.ipynb b/AGNewsEvaluation.ipynb → AGNewsDataset/AGNewsEvaluation.ipynb
diff --git a/AGNewsDataset/train.csv b/AGNewsDataset/train.csv
diff --git a/README.md b/README.md
@@ -0,0 +1,21 @@
+## *Text Classification Using Unsupervised Learning Techniques*
+
+This code complements my diploma thesis on "Text Classification Using Unsupervised Learning Techniques" for the Electrical and Computer Engineering Department of Aristotle University of Thessaloniki, Greece.
+
+Author: Kitsios Konstantinos
+
+Correspondance address: [email protected]
+
+Code sub-routines and pretrained neural networks are used from the research papers below:
+
+[1]: D. Cer, Y. Yang, S. yi Kong, N. Hua, N. Limtiaco, R. S. John, N. Constant,M. Guajardo-Cespedes, S. Yuan, C. Tar, Y.-H. Sung, B. Strope, and R. Kurzweil, ‘‘Universal sentence encoder,’’arXiv preprint arXiv:1803.11175, 2018.
+
+[2]: A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever, ‘‘Language models areunsupervised multitask learners,’’, 2019.
+
+[3]: N. Pitsianis, A. Iliopoulos, D. Floros, and X. Sun, ‘‘Spaceland embedding of sparse stochastic graphs,’’2019 IEEE High Performance Extreme Computing Conference (HPEC),pp. 1-8, 2019.
+
+### Setup
+The packages needed in order to run the code are in the *requirements.txt* file and you can install the through pip by running
+`pip install requirements.txt`
+
+The code for each dataset can be executed from the associated notebook (.ipynb)