Ahora estás siguiendo a
Error al seguir a usuario.
Este usuario no permite que los usuarios lo sigan.
Ya estás siguiendo a este usuario.
Tu plan de membresía solo permite 0 seguimientos. Mejora tu membresía aquí.
Dejaste de seguir correctamente a
Error al dejar de seguir al usuario.
Has recomendado exitosamente a
Error al recomendar al usuario.
Algo salió mal. Por favor, actualiza la página e intenta de nuevo.
Email verificado correctamente.
thessaloniki,
greece
Aquí son las 10:19 a. m.
Se unió el febrero 20, 2017
0 Recomendaciones
Dimitris D.
@dimitriscontia
0,0
0,0
0%
0%
thessaloniki,
greece
N/A
Trabajos finalizados
N/A
Dentro del presupuesto
N/A
A tiempo
N/A
Tasa de recontratación
Language Processing R&D / Full Stack Web Developer
Contacta Dimitris D. sobre tu trabajo
Inicia sesión para comentar cualquier detalle por chat.
Comentarios
Cambios guardados
¡No hay comentarios para ver aquí!
Experiencia
Co-Founder R&D
feb 2017 - Presente
I am a co-founder at Contia Corporation, which was founded in Greece. Our focus lies in developing websites and e-commerce platforms using cutting-edge web technologies. We prioritize excellent communication and providing dedicated support to our clients.
Exploitation of Cultural Assets with computer-assisted Recognition, Labeling and meta-data ...
ene 2018 - sept 2021 (3 años, 8 meses)
The position involves applying semantic indexing to Greek literature, with a specific focus on designing a deep learning architecture for genre identification. This task poses several challenges, including the use of non-modern Greek language and the presence of noisy text resulting from OCR applied to digital books. Additionally, this is a multi-class classification problem.
Large Scale Semantic Indexing and Question Answering
ene 2015 - ene 2019 (4 años)
The objective of this project was to thoroughly examine existing question-answering systems and introduce novel approaches. Additionally, we sought to create a domain-specific end-to-end question-answering system. This endeavor involved the utilization of various paradigms and programming languages. We constructed learning models through machine learning techniques and employed natural language processing to encode texts.
Educación
PhD
(7 años)
Informatics and Communications (Knowledge, Data and Software Technologies)
(2 años)
Informatics
(4 años)
Calificaciones
Question Answering Award
BioASQ
2019
I took part in the BioASQ Challenge, specifically in the question-answering task. The goal was to provide answers to questions written in natural language, based on a set of related passages. I achieved a position in three out of five test batches.
Question Answering Award
BioASQ
2018
I participated in BioASQ Challenge in the task of question answering. The aim was to answer questions written in the natural language given a set of related passages. I got a position in four of five test batches.
Question Answering Award
BioASQ
2017
I participated in BioASQ Challenge in the task of question answering. The aim was to answer questions written in the natural language given a set of related passages. I got a position in one of five test batches.
Publicaciones
Enhancing yes/no question answering with weak supervision via extractive question answering
Springer
Recent studies indicate that models pre-trained on large corpora and fine-tuned on task-specific datasets, covering multiple tasks, can generate remarkable results across various benchmarks. We propose a new approach based on a straightforward hypothesis: improving model performance on a target task by considering other artificial tasks defined on the same training dataset.
Artificial fine-tuning tasks for yes/no question answering
Cambridge University Press
Current research in yes/no QA focuses on transfer learning and transformer-based models. Models trained on large corpora are fine-tuned on tasks similar to yes/no QA, and the knowledge is then transferred. This paper proposes using artificial yes/no tasks to enhance performance. Three tasks were adapted for this purpose. This offers a creative and flexible approach to improving yes/no QA models by leveraging existing tasks and datasets.
Word embeddings and external resources for answer processing in biomedical factoid question ....
Academic Press
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.
Yes/No Question Answering in BioASQ 2019
Springer International Publishing
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.
Semantic Indexing of 19th-Century Greek Literature Using 21st-Century Linguistic Resources
Multidisciplinary Digital Publishing Institute
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.
Large-scale semantic indexing and question answering in biomedicine
In Proceedings of the Fourth BioASQ workshop
I extended my previous work on answer processing component.
Ensemble Approaches for Large-Scale Multi-Label Classification and Question Answering in Biomedicine
CLEF (working notes)
I implemented an answer processing component applied in biomedicine for a competition called BioASQ. In this paper I describe my work.
Contacta Dimitris D. sobre tu trabajo
Inicia sesión para comentar cualquier detalle por chat.
Verificaciones
Principales habilidades
Explorar freelancers similares
Explorar galerías similares
¡Invitación enviada correctamente!
¡Gracias! Te hemos enviado un enlace para reclamar tu crédito gratuito.
Algo salió mal al enviar tu correo electrónico. Por favor, intenta de nuevo.
Falló el copiado al portapapeles. Intenta de nuevo después de ajustar tus permisos.
Copiado al portapapeles.
Cargando visualización previa
Permiso concedido para Geolocalización.
Tu sesión de acceso ha expirado y has sido desconectado. Por favor, inica sesión nuevamente.