Manolis Koubarakis

Alexandros Zeakis, George Papadakis, Dimitrios Skoutas et al.

Many recent works on Entity Resolution (ER) leverage Deep Learning techniques involving language models to improve effectiveness. This is applied to both main steps of ER, i.e., blocking and matching. Several pre-trained embeddings have been tested, with the most popular ones being fastText and variants of the BERT model. However, there is no detailed analysis of their pros and cons. To cover this gap, we perform a thorough experimental analysis of 12 popular language models over 17 established benchmark datasets. First, we assess their vectorization overhead for converting all input entities into dense embeddings vectors. Second, we investigate their blocking performance, performing a detailed scalability analysis, and comparing them with the state-of-the-art deep learning-based blocking method. Third, we conclude with their relative performance for both supervised and unsupervised matching. Our experimental results provide novel insights into the strengths and weaknesses of the main language models, facilitating researchers and practitioners to select the most suitable ones in practice.

Angelos Poulis, Eleni Tsalapati, Manolis Koubarakis

Recent advancements in transformer-based models have initiated research interests in investigating their ability to learn to perform reasoning tasks. However, most of the contexts used for this purpose are in practice very simple: generated from short (fragments of) first-order logic sentences with only a few logical operators and quantifiers. In this work, we construct the natural language dataset, DELTA$_D$, using the description logic language $\mathcal{ALCQ}$. DELTA$_D$ contains 384K examples, and increases in two dimensions: i) reasoning depth, and ii) linguistic complexity. In this way, we systematically investigate the reasoning ability of a supervised fine-tuned DeBERTa-based model and of two large language models (GPT-3.5, GPT-4) with few-shot prompting. Our results demonstrate that the DeBERTa-based model can master the reasoning task and that the performance of GPTs can improve significantly even when a small number of samples is provided (9 shots). We open-source our code and datasets.

Niloy Ganguly, Dren Fazlija, Maryam Badar et al.

State-of-the-art AI models largely lack an understanding of the cause-effect relationship that governs human understanding of the real world. Consequently, these models do not generalize to unseen data, often produce unfair results, and are difficult to interpret. This has led to efforts to improve the trustworthiness aspects of AI models. Recently, causal modeling and inference methods have emerged as powerful tools. This review aims to provide the reader with an overview of causal methods that have been developed to improve the trustworthiness of AI models. We hope that our contribution will motivate future research on causality-based solutions for trustworthy AI.

Dimitra Panou, Alexandros C. Dimopoulos, Manolis Koubarakis et al.

Biomedical text mining and question-answering are essential yet highly demanding tasks, particularly in the face of the exponential growth of biomedical literature. In this work, we present our participation in the 13th edition of the BioASQ challenge, which involves biomedical semantic question-answering for Task 13b and biomedical question-answering for developing topics for the Synergy task. We deploy a selection of open-source large language models (LLMs) as retrieval-augmented generators to answer biomedical questions. Various models are used to process the questions. A majority voting system combines their output to determine the final answer for Yes/No questions, while for list and factoid type questions, the union of their answers in used. We evaluated 13 state-of-the-art open source LLMs, exploring all possible model combinations to contribute to the final answer, resulting in tailored LLM pipelines for each question type. Our findings provide valuable insight into which combinations of LLMs consistently produce superior results for specific question types. In the four rounds of the 2025 BioASQ challenge, our system achieved notable results: in the Synergy task, we secured 1st place for ideal answers and 2nd place for exact answers in round 2, as well as two shared 1st places for exact answers in round 3 and 4.

Angelos Poulis, Eleni Tsalapati, Manolis Koubarakis

Recent advancements in transformer-based language models have sparked research into their logical reasoning capabilities. Most of the benchmarks used to evaluate these models are simple: generated from short (fragments of) first-order logic sentences with only a few logical operators and quantifiers. We construct the natural language dataset, DELTA$_D$, using the expressive description logic language $\mathcal{ALCQ}$. DELTA$_D$ comprises 384K examples and increases in two dimensions: i) reasoning depth, and ii) linguistic complexity. In this way, we systematically investigate the logical reasoning capabilities of a supervised fine-tuned DeBERTa-based model and two large language models (GPT-3.5, GPT-4) with few-shot prompting. We show that the DeBERTa-based model fine-tuned on our dataset can master the entailment checking task. Moreover, the performance of GPTs can improve significantly even when a small number of samples is provided (9 shots). We open-source our code and datasets.

Sergios-Anestis Kefalidis, Konstantinos Plas, Manolis Koubarakis

TerraQ is a spatiotemporal question-answering engine for satellite image archives. It is a natural language processing system that is built to process requests for satellite images satisfying certain criteria. The requests can refer to image metadata and entities from a specialized knowledge base (e.g., the Emilia-Romagna region). With it, users can make requests like "Give me a hundred images of rivers near ports in France, with less than 20% snow coverage and more than 10% cloud coverage", thus making Earth Observation data more easily accessible, in-line with the current landscape of digital assistants.

Christos Papaloukas, Ilias Chalkidis, Konstantinos Athinaios et al.

In this work, we study the task of classifying legal texts written in the Greek language. We introduce and make publicly available a novel dataset based on Greek legislation, consisting of more than 47 thousand official, categorized Greek legislation resources. We experiment with this dataset and evaluate a battery of advanced methods and classifiers, ranging from traditional machine learning and RNN-based methods to state-of-the-art Transformer-based methods. We show that recurrent architectures with domain-specific word embeddings offer improved overall performance while being competitive even to transformer-based models. Finally, we show that cutting-edge multilingual and monolingual transformer-based models brawl on the top of the classifiers' ranking, making us question the necessity of training monolingual transfer learning models as a rule of thumb. To the best of our knowledge, this is the first time the task of Greek legal text classification is considered in an open research project, while also Greek is a language with very limited NLP resources in general.

Dharmen Punjani, Markos Iliakis, Theodoros Stefou et al.

Large amounts of geospatial data have been made available recently on the linked open data cloud and the portals of many national cartographic agencies (e.g., OpenStreetMap data, administrative geographies of various countries, or land cover/land use data sets). These datasets use various geospatial vocabularies and can be queried using SPARQL or its OGC-standardized extension GeoSPARQL. In this paper, we go beyond these approaches to offer a question-answering engine for natural language questions on top of linked geospatial data sources. Our system has been implemented as re-usable components of the Frankenstein question answering architecture. We give a detailed description of the system's architecture, its underlying algorithms, and its evaluation using a set of 201 natural language questions. The set of questions is offered to the research community as a gold standard dataset for the comparative evaluation of future geospatial question answering engines.

Efi Karra Taniskidou, George Papadakis, George Giannakopoulos et al.

Microblogging platforms constitute a popular means of real-time communication and information sharing. They involve such a large volume of user-generated content that their users suffer from an information deluge. To address it, numerous recommendation methods have been proposed to organize the posts a user receives according to her interests. The content-based methods typically build a text-based model for every individual user to capture her tastes and then rank the posts in her timeline according to their similarity with that model. Even though content-based methods have attracted lots of interest in the data management community, there is no comprehensive evaluation of the main factors that affect their performance. These are: (i) the representation model that converts an unstructured text into a structured representation that elucidates its characteristics, (ii) the source of the microblog posts that compose the user models, and (iii) the type of user's posting activity. To cover this gap, we systematically examine the performance of 9 state-of-the-art representation models in combination with 13 representation sources and 3 user types over a large, real dataset from Twitter comprising 60 users. We also consider a wide range of 223 plausible configurations for the representation models in order to assess their robustness with respect to their internal parameters. To facilitate the interpretation of our experimental results, we introduce a novel taxonomy of representation models. Our analysis provides novel insights into the performance and functionality of the main factors determining the performance of content-based recommendation in microblogs.

Lefteris Zervakis, Christos Tryfonopoulos, Antonios Papadakis-Pesaresi et al.

We envision a publish/subscribe ontology system that is able to index millions of user subscriptions and filter them against ontology data that arrive in a streaming fashion. In this work, we propose a SPARQL extension appropriate for a publish/subscribe setting; our extension builds on the natural semantic graph matching of the language and supports the creation of full-text subscriptions. Subsequently, we propose a main-memory subscription indexing algorithm which performs both semantic and full-text matching at low complexity and minimal filtering time. Thus, when ontology data are published matching subscriptions are identified and notifications are forwarded to users.