A Case Study of NLG from Multimedia Data Sources: Generating Architectural Landmark Descriptions

no code implementations • ACL (WebNLG, INLG) 2020 • Simon Mille, Spyridon Symeonidis, Maria Rousi, Montserrat Marimon Felipe, Klearchos Stavrothanasopoulos, Petros Alvanitopoulos, Roberto Carlini Salguero, Jens Grivolla, Georgios Meditskos, Stefanos Vrochidis, Leo Wanner

In this paper, we present a pipeline system that generates architectural landmark descriptions using textual, visual and structured data.

Retrieval

LARD: Large-scale Artificial Disfluency Generation

1 code implementation • LREC 2022 • Tatiana Passali, Thanassis Mavropoulos, Grigorios Tsoumakas, Georgios Meditskos, Stefanos Vrochidis

In addition, we release a new large-scale dataset with disfluencies that can be used on four different tasks: disfluency detection, classification, extraction, and correction.

Neural Crystals

no code implementations • 5 Sep 2023 • Sofia Karamintziou, Thanassis Mavropoulos, Dimos Ntioudis, Georgios Meditskos, Stefanos Vrochidis, Ioannis, Kompatsiaris

We face up to the challenge of explainability in Multimodal Artificial Intelligence (MMAI).

User Identity Linkage in Social Media Using Linguistic and Social Interaction Features

no code implementations • 22 Aug 2023 • Despoina Chatzakou, Juan Soler-Company, Theodora Tsikrika, Leo Wanner, Stefanos Vrochidis, Ioannis Kompatsiaris

Social media users often hold several accounts in their effort to multiply the spread of their thoughts, ideas, and viewpoints.

Keyphrase Extraction using Textual and Visual Features

no code implementations • WS 2014 • Yaakov HaCohen-Kerner, Stefanos Vrochidis, Dimitris Liparas, Anastasia Moumtzidou, Ioannis Kompatsiaris

Keyphrase Extraction Text Summarization

Concept-oriented labelling of patent images based on Random Forests and proximity-driven generation of synthetic data

no code implementations • WS 2014 • Dimitris Liparas, Anastasia Moumtzidou, Stefanos Vrochidis, Ioannis Kompatsiaris

Image Retrieval Information Retrieval