Dimitris Dimitriadis

Language Processing R&D

Full Stack Web Developer

Dimitris Dimitriadis

Language Processing R&D

Full Stack Web Developer

About Me

Hello! I’m Dimitris Dimitriadis.

Currently, I’m a PhD student at Aristotle University of Thessaloniki in Greece studying Natural Language Processing and Machine Learning. I am also one of the owners of a three-year old company, called Contia, oriented towards Web Development. I focus on new technologies and it is my interest to participate in innovative ideas and projects. I love to solve problems.

  • Age: 29
  • Residence: Greece
  • Freelance: Available
  • Address: Thessaloniki, Greece
My Services
Designing and Developing Machine Learning Systems

Experience in (1) developing machine learning applications according to requirements, (2) selecting appropriate datasets and data representation methods, (3) running machine learning tests and experiments and (4) performing statistical analysis and fine-tuning.

Solving Natural Language Processing and Text Mining Tasks

Working on several tasks such as named-entity recognition, question answering, sentiment analysis and textual entailment. Experience both in traditional machine learning techniques and deep learning approches. Expertise in question answering applied on biomedical scientific publications.

Desktop App Development

Excellent programming skills in Python with good knowledge of open source frameworks for NLP and deep learning such as NLTK, spacy, numpy, keras and scikit learn. Experience with Java, C and C++. Basic knowledge on Matlab, VB and Visual C++.

Web Development

Front-end development with CSS/HTML/JS using mainly the Bootstrap framework. Back-end development with python (Django Framework) or pure php. Experience also with Wordpress. Application of MVC design pattern.

Pricing
Web Development
15 hour
  • Wordpress
  • SEO Optimization
  • Custom Web Design
  • Custom Programming Scripts
Advanced Web Development
25 hour
  • Coding From Scratch
  • Project Planning
  • Python/PHP/Apache
  • JS/CSS/HTML
Machine Learning & Development
35 hour
  • Building Learning Models
  • Research on task
  • Clean Code
  • Experiments on Datasets / Tuning models
Fun Facts
2 Academic Projects
5 Awards Won
5 000+ Cups Of Coffee
2 Countries Visited
200+ Solutions
Resume
Academic Experience
ECARLE Project
2018 - 2021
ECARLE Project
Exploitation of Cultural Assets with computer-assisted Recognition, Labeling and meta-data Enrichment

I’m working on semantic indexing applied to Greek literature. Particularly, the aim of my task is the designing of a deep learning architecture for solving the task of genre identification. It is a multi-class problem, while the difficulties of the tasks are (1) the language, which is not modern Greek and (2) the quality of the text. Text is very noisy due to the fact that it comes from OCR applied to digital books. Research Results p.34

Large Scale Semantic Indexing and Question Answering
2015-2019
Large Scale Semantic Indexing and Question Answering
In cooperation with Atypon Systems, LLC

I had mainly worked on Question Answering applied in biomedical domain. Particulalrly, my aim was the conceptualization of QA studying the related works around of this topic, building several learning models, developing new algorithms and integrating several resources.

2016 - 2020
Lab Assistant
Object Oriented Programming (Java)

My responsibilities are to:

  1. teach students Java programming language, in practise.
  2. admin GitHub classroom to evaluate the students’ performance.
  3. help students to understand object oriented programming.
EDUCATION
2015-Present
PhD Student
Natural Language processing and Knowledge Extraction from Unstructured Text

I’m studying at Aristotle University of Thessaloniki in Greece. My supervisor is prof. Greg Tsoumakas.

2014- 2016
Msc Informatics and Communications
Knowledge, Data and Software Technologies

Some of the courses that I had attended

  1. Distributed Resource Management (Apache Hadoop, MapReduce)
  2. Advanced Algorithms (e.g. hashing algorithms in detail)
  3. Advanced Machine Learning ( e.g. Bagging, Boosting etc.)
  4. SPSS
  5. Semantic Web (e.g. RDF schema, etc)
2010 - 2014
Bachelor School of Informatics
Information Systems

I had studied at Aristotle University of Thessaloniki in the departure of School of Informatics. My expertise was on Information Systems. Particularly, we were working on data structures, algorithms, programming, web development and a lot of maths.

Jobs
2016 - Present
Private Tutor
Academic Lessons / Support on Academic Exercises, Theses
2014-2016
IT member
Media Markt Thessaloniki
  1. Technical Support
  2. Customer Service
Languages
2016
German
Goethe (B1)
2010
English
Michigan (B2)
  • Presentations (e.g. Conference Article )
  • Writing (e.g. Journal Article, Reports )
  • Communication (e.g. via Google Hangouts, Skype, f2f)
Challenges
BioASQ Challenge
2014 - 2019
BioASQ Challenge
Task B, Phase (Question Answering, exact answers)

Several awards:

  1. 2/5 test batches (2014)
  2. 2/5 test batches (2016)
  3. 1/5 test batches (2017)
  4. 4/5 test batches (2018) 
  5. 3/5 test batches (2019)
Certificates
2022
Continuous Engineering and Deep Learning for Trustworthy Autonomous Systems
Summer School

Deep learning has developed into a mature technology and it is nowadays an essential part in systems that may include timing and cyber-physical components, such as self-driving cars, autonomous control systems in medical applications and so on. We call these systems learning-enabled autonomous systems and we focus on key challenges in their design and development, which lie in the intersection of the two H2020 research projects that jointly organize this one-week summer school with prominent invited speakers and hands-on sessions on related tools and state-of-the-art industrial technologies.

Other
2018
Basic Life Support
2011
Braille
2001-2013
Basktball Player
Volunteering
2020
DS2020 Conference
organization team

I was in the organization team of DS2020 Conference. My responsibilities were:

  1. To setup a new account on slack and add channels related with the sessions of the conference. I also had to configure the permissions and invited the attendees. I was there to solve any issue with the participants and give guidelines about the conference.
  2. To walk in the gather town and help the participants to find the rooms giving them directions and also answering their questions.
  3. To control the discussion at the zoom platform. I welcomed the speakers and I was also there to solve any technical issue.
My Skills
Research
  • Question Answering
  • Natural Language Processing
  • Machine Learning
  • Deep Learning
Coding
  • Python / Php / JS / CSS / HTML
  • Java
  • C++ / C
  • Matlab / VB / VC++
Academic Articles
Journals
Artificial fine-tuning tasks for yes/no question answering
2022
Artificial fine-tuning tasks for yes/no question answering
D. Dimitriadis, G. Tsoumakas

Current research in yes/no question answering (QA) focuses on transfer learning techniques and transformer-based models. Models trained on large corpora are fine-tuned on tasks similar to yes/no QA, and then the captured knowledge is transferred for solving the yes/no QA task. Most previous studies use existing similar tasks, such as natural language inference or extractive QA, for the fine-tuning step. This paper follows a different perspective, hypothesizing that an artificial yes/no task can transfer useful knowledge for improving the performance of yes/no QA. We introduce three such tasks for this purpose, by adapting three corresponding existing tasks: candidate answer validation, sentiment classification, and lexical simplification. Furthermore, we experimented with three different variations of the BERT model (BERT base, RoBERTa, and ALBERT). The results show that our hypothesis holds true for all artificial tasks, despite the small size of the corresponding datasets that are used for the fine-tuning process, the differences between these tasks, the decisions that we made to adapt the original ones, and the tasks’ simplicity. This gives an alternative perspective on how to deal with the yes/no QA problem, that is more creative, and at the same time more flexible, as it can exploit multiple other existing tasks and corresponding datasets to improve yes/no QA models.
Link

Semantic Indexing of 19th-Century Greek Literature Using 21st-Century Linguistic Resources
2021
Semantic Indexing of 19th-Century Greek Literature Using 21st-Century Linguistic Resources
D. Dimitriadis, S. Zapounidou, G. Tsoumakas

Manual classification of works of literature with genre/form concepts is a time-consuming
task requiring domain expertise. Building automated systems based on language understanding
can help humans to achieve this work faster and more consistently. Towards this direction, we
present a case study on automatic classification of Greek literature books of the 19th century. The
main challenges in this problem are the limited number of literature books and resources of that
age and the quality of the source text. We propose an automated classification system based on the
Bidirectional Encoder Representations from Transformers (BERT) model trained on books from the
20th and 21st century. We also dealt with BERT’s constraint on the maximum sequence length of
the input, leveraging the TextRank algorithm to construct representative sentences or phrases from
each book. The results show that BERT trained on recent literature books correctly classifies most of
the books of the 19th century despite the disparity between the two collections. Additionally, the
TextRank algorithm improves the performance of BERT.

Word Embeddings and External Resources for Answer Processing in Biomedical Factoid Question Answering
2019
Word Embeddings and External Resources for Answer Processing in Biomedical Factoid Question Answering
D. Dimitriadis, G. Tsoumakas

Biomedical question answering (QA) is a challenging task that has not been yet successfully solved, according to results on international benchmarks, such as BioASQ. Recent progress on deep neural networks has led to promising results in domain independent QA, but the lack of large datasets with biomedical question-answer pairs hinders their successful application to the domain of biomedicine.

We propose a novel machine-learning based answer processing approach that exploits neural networks in an unsupervised way through word embeddings. Our approach first combines biomedical and general purpose tools to identify the candidate answers from a set of passages. Candidates are then represented using a combination of features based on both biomedical external resources and input textual sources, including features based on word embeddings. Candidates are then ranked based on the score given at the output of a binary classification model, trained from candidates extracted from a small number of questions, related passages and correct answer triplets from the BioASQ challenge.

Our experimental results show that the use of word embeddings, combined with other features, improves the performance of answer processing in biomedical question answering. In addition, our results show that the use of several annotators improves the identification of answers in passages. Finally, our approach has participated in the last two versions (2017, 2018) of the BioASQ challenge achieving competitive results.

Workshops
2020
Yes/No Question Answering in BIoASQ 2019
Dimitris Dimitriadis, Grigorios Tsoumakas

The field of question answering has gained greater attention with the rise of deep neural networks. More and more approaches adopt paradigms which are based primarily on the powerful language representations models and transfer learning techniques to build efficient learning models which are able to outperform current state of the art systems. Endorsing this current trend, in this paper, we strive to take a step towards the goal of answering yes/no questions in the field of biomedicine. Specifically, the task is to give a short answer (yes or no) for a question written in natural language, finding clues including in a set of snippets that are related with this question. We propose three different deep neural network models, which are free of assumptions about predefined specific feature functions, while the key elements of these are the ELMo embeddings, the similarity matrices and/or sentiment information. The results have shown that incorporating the sentiment, we can improve the performance of a yes/no question answering system while the proposed learning models significantly outperform the BioASQ baseline.

2016
Large-scale semantic indexing and question answering in biomedicine
Eirini Papagiannopoulou, Yiannis Papanikolaou, Dimitris Dimitriadis, Sakis Lagopoulos, Grigorios Tsoumakas, Manos Laliotis, Nikos Markantonatos, Ioannis Vlahavas

In this paper we present the methods and approaches employed in terms of our participation in the 2016 version of the BioASQ challenge. For the semantic indexing task, we extended our successful ensemble approach of last year with additional models. The official results obtained so-far demonstrate a continuing consistent advantage of our approaches against the National Library of Medicine (NLM) baselines. For the question answering task, we extended our approach on factoid questions, while we also developed approaches for the document, concept and snippet retrieval sub-tasks

2014
Ensemble Approaches for Large-Scale Multi-Label Classification and Question Answering in Biomedicine.
Yannis Papanikolaou, Dimitrios Dimitriadis, Grigorios Tsoumakas, Manos Laliotis, Nikos Markantonatos, Ioannis P Vlahavas

This paper documents the systems that we developed for our participation in the BioASQ 2014 large-scale bio-medical semantic indexing and question answering challenge. For the large-scale semantic indexing task, we employed a novel multi-label ensemble method consisting of support vector machines, labeled Latent Dirichlet Allocation models and meta-models predicting the number of relevant labels. This method proved successful in our experiments as well as during the competition. For the question answering task we combined different techniques for scoring of candidate answers based on recent literature.

Conferences
2022
Development of a Mobile Application to Calculate the River Flow with the Mid-section Method (in greek)
Dimitrios Pantelakis, Dimitris Dimitriadis, Konstantinos Dimitriadis, Xaralampos Doulgeris, Euaggelos Hatzigiannakis

The design and development of mobile applications in the environmental sciences is expanding. This work presents the design and implementation of a mobile application in Android platform that aims to calculate the river flow (on time) with the Mid-Section method and the storage of measurement data and results in databases. The Kotlin and Python programming languages have been used for application development. This application is innovative in the field of hydrometers and its development aims to directly calculate the flow of a river.

Recent Works
Latest Posts
23 August 2020 Estimating Running Time of an Algorithm using Simple Rules.

To estimate the running time of an algorithm and the difference of the algorithm against others, we make a strong…

9 February 2020 Deterministic Finite State Automota for Regular Expressions

A finite state automaton (FSA) is a computational model and is defined by the following 5 parameters: Q: a finite…

28 January 2020 Google Apps for Education (Aristotle University of Thessaloniki)

Google supports students and researchers (academic staff, in general) offering some of their services for free. In Aristotle University of…

2 November 2019 Datasets In Question Answering

Question Answering (QA) is an AI-complete problem meaning that the current state-of-the-art approaches can not solve it. One of the…

Get in Touch
  • Address: Tsimiski 17, Thessaloniki, Greece
  • Email: dimitrisqa@gmail.com
  • Freelance: Available
Contact Form