ΕΕΛΛΑΚ - Λίστες Ταχυδρομείου

[GSOC 24]: Greeklish-to-Greek: Development of an open-source and state-of-the-art toolkit

  • Subject: [GSOC 24]: Greeklish-to-Greek: Development of an open-source and state-of-the-art toolkit
  • From: Dimitrios Foteinos <dimfwteinos [ at ] gmail [ dot ] com>
  • Date: Mon, 1 Apr 2024 16:56:30 +0300
Greetings all!

Dear Dr. John Pavlopoulos, Dr. Ion Androutsopoulos, Mr. Stavros Vassos and
Mr. Lefteris Loukas,

My name is Dimitrios and the previous year I graduated from NKUA (National
and Kapodistrian University of Athens), holding a BSc in Informatics &
Telecommunications department. After a thorough examination of all the
proposed projects, I've found your project the most interesting one
(according to my research interest), with respect to all the other projects
and mentors.

I've been working as a Data Scientist for 1,5 year and also I've done my
internship in NCSR Demokritos.
Through my academic journey and personal projects, I've developed a strong
foundation in advanced Python programming, Software Engineering, and
mostly, Deep Learning for NLP, with practical experience.

Some of my most relevant projects that you may find relevant are:


   1. Sentiment Classifier using a *Bidirectional Stacked RNN*, with
   *LSTM/GRU* cells (from Applied Deep Learning on NLP tasks from *Dr.
   Manolis Koubarakis* University Course)
   2. Document Retrieval System to return titles of scientific papers (from
   Applied Deep Learning on NLP tasks from *Dr. Manolis Koubarakis* University
   Course)
   3. Truthfulness Multi-class Classification (Personal project, using a
   provided dataset from Satalia <https://www.satalia.com/>).
   4. Tag Prediction / Multi-label Classification (Personal project, using
   a provided dataset from Kaggle
   <https://www.kaggle.com/code/miljan/predicting-tags-for-stackoverflow>).

I'd be happy to invite you to my private repositories on Github and
demonstrate you those projects.

I am particularly drawn to the aspect of the project that involves
utilizing recent LLMs, such as Meta's LLaMA2, Mistral Models, or the recent
LLM, Gemma, with respect to the available computational resources, to
innovate new methods for Greeklish-to-Greek conversion. Also, the work of
GreekLex <https://psychology.nottingham.ac.uk/greeklex/greeklex1.html> could
be helpful.

I look forward to the possibility of discussing how I can contribute to the
project further.

Please feel free to contact me if you require any additional information or
to arrange a meeting. My proposal will be submitted today.

Thank you for considering my application.

----------------------------------------------------------------------------------------------------------------------

Contact info:


   - CV:
   https://drive.google.com/file/d/1YSkRCLOyXofIWkVts6PEnoHVCW14Lb2v/view?usp=sharing
   - Github: https://github.com/dfwteinos
   - LinkedIn: https://www.linkedin.com/in/dimitrios-foteinos-9008941b8/
----
Λαμβάνετε αυτό το μήνυμα απο την λίστα: Λίστα αλληλογραφίας και συζητήσεων που απευθύνεται σε φοιτητές developers \& mentors έργων του Google Summer of Code - A discussion list for student developers and mentors of Google Summer of Code projects.,
https://lists.ellak.gr/gsoc-developers/listinfo.html
Μπορείτε να απεγγραφείτε από τη λίστα στέλνοντας κενό μήνυμα ηλ. ταχυδρομείου στη διεύθυνση <gsoc-developers+unsubscribe [ at ] ellak [ dot ] gr>.