arXiv subjects

Zeyd Boukhers

Publications and source records attributed to Zeyd Boukhers.

At least 37 records · Page 2Linked to original sources

arXiv2025

ELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports

Europe's healthcare systems require enhanced interoperability and digitalization, driving a demand for innovative solutions to process legacy clinical data. This paper presents the results of our project, which aims to leverage Large Language Models (LLMs) to extract structured information from unstructured clinical reports, focusing on patient history, diagnoses, treatments, and other predefined categories. We developed a workflow with a user interface and evaluated LLMs of varying sizes through prompting strategies and fine-tuning. Our results show that fine-tuned smaller models match or surpass larger counterparts in performance, offering efficiency for resource-limited settings. A new dataset of 60,000 annotated English clinical summaries and 24,000 German translations was validated with automated and manual checks. The evaluations used ROUGE, BERTScore, and entity-level metrics. The work highlights the approach's viability and outlines future improvements.

cs.CL↗

arXiv2025

Comparison of Feature Learning Methods for Metadata Extraction from PDF Scholarly Documents

The availability of metadata for scientific documents is pivotal in propelling scientific knowledge forward and for adhering to the FAIR principles (i.e. Findability, Accessibility, Interoperability, and Reusability) of research findings. However, the lack of sufficient metadata in published documents, particularly those from smaller and mid-sized publishers, hinders their accessibility. This issue is widespread in some disciplines, such as the German Social Sciences, where publications often employ diverse templates. To address this challenge, our study evaluates various feature learning and prediction methods, including natural language processing (NLP), computer vision (CV), and multimodal approaches, for extracting metadata from documents with high template variance. We aim to improve the accessibility of scientific documents and facilitate their wider use. To support our comparison of these methods, we provide comprehensive experimental results, analyzing their accuracy and efficiency in extracting metadata. Additionally, we provide valuable insights into the strengths and weaknesses of various feature learning and prediction methods, which can guide future research in this field.

cs.IR↗

arXiv2024

From Theory to Practice: Demonstrators of FAIR Data Spaces Across Different Sectors

The principles of data spaces for sovereign data exchange across trusted organizations have so far mainly been adopted in business-to-business settings, and recently scaled to cloud environments. Meanwhile, research organizations have established distributed research data infrastructures, respecting the principle that data must be FAIR, i.e., findable, accessible, interoperable and reusable. For mutual benefit of these two communities, the FAIR Data Spaces project aims to connect them towards the vision of a common, cloud-based data space for industry and research. Thus, the project establishes a common legal and ethical framework, common technical building blocks, and it demonstrates the orchestration of multiple building blocks in self-contained settings addressing a diverse range of use cases in domains including health, biodiversity, and engineering. This paper gives a summary of all demonstrators, ranging from research data infrastructures scaled to industry-ready cloud environments to work in progress on building bridges between operational business-to-business data spaces and research data infrastructures.

cs.DC↗

arXiv2024

Large Language Model in Medical Informatics: Direct Classification and Enhanced Text Representations for Automatic ICD Coding

Addressing the complexity of accurately classifying International Classification of Diseases (ICD) codes from medical discharge summaries is challenging due to the intricate nature of medical documentation. This paper explores the use of Large Language Models (LLM), specifically the LLAMA architecture, to enhance ICD code classification through two methodologies: direct application as a classifier and as a generator of enriched text representations within a Multi-Filter Residual Convolutional Neural Network (MultiResCNN) framework. We evaluate these methods by comparing them against state-of-the-art approaches, revealing LLAMA's potential to significantly improve classification outcomes by providing deep contextual insights into medical texts.

cs.LG↗

arXiv2024

Beyond Trading Data: The Hidden Influence of Public Awareness and Interest on Cryptocurrency Volatility

Since Bitcoin first appeared on the scene in 2009, cryptocurrencies have become a worldwide phenomenon as important decentralized financial assets. Their decentralized nature, however, leads to notable volatility against traditional fiat currencies, making the task of accurately forecasting the crypto-fiat exchange rate complex. This study examines the various independent factors that affect the volatility of the Bitcoin-Dollar exchange rate. To this end, we propose CoMForE, a multimodal AdaBoost-LSTM ensemble model, which not only utilizes historical trading data but also incorporates public sentiments from related tweets, public interest demonstrated by search volumes, and blockchain hash-rate data. Our developed model goes a step further by predicting fluctuations in the overall cryptocurrency value distribution, thus increasing its value for investment decision-making. We have subjected this method to extensive testing via comprehensive experiments, thereby validating the importance of multimodal combination over exclusive reliance on trading data. Further experiments show that our method significantly surpasses existing forecasting tools and methodologies, demonstrating a 19.29% improvement. This result underscores the influence of external independent factors on cryptocurrency volatility.

q-fin.ST↗

arXiv2024

Falcon 7b for Software Mention Detection in Scholarly Documents

This paper aims to tackle the challenge posed by the increasing integration of software tools in research across various disciplines by investigating the application of Falcon-7b for the detection and classification of software mentions within scholarly texts. Specifically, the study focuses on solving Subtask I of the Software Mention Detection in Scholarly Publications (SOMD), which entails identifying and categorizing software mentions from academic literature. Through comprehensive experimentation, the paper explores different training strategies, including a dual-classifier approach, adaptive sampling, and weighted loss scaling, to enhance detection accuracy while overcoming the complexities of class imbalance and the nuanced syntax of scholarly writing. The findings highlight the benefits of selective labelling and adaptive sampling in improving the model's performance. However, they also indicate that integrating multiple strategies does not necessarily result in cumulative improvements. This research offers insights into the effective application of large language models for specific tasks such as SOMD, underlining the importance of tailored approaches to address the unique challenges presented by academic text analysis.

cs.LG↗

arXiv2024

Gyroscope-Assisted Motion Deblurring Network

Image research has shown substantial attention in deblurring networks in recent years. Yet, their practical usage in real-world deblurring, especially motion blur, remains limited due to the lack of pixel-aligned training triplets (background, blurred image, and blur heat map) and restricted information inherent in blurred images. This paper presents a simple yet efficient framework to synthetic and restore motion blur images using Inertial Measurement Unit (IMU) data. Notably, the framework includes a strategy for training triplet generation, and a Gyroscope-Aided Motion Deblurring (GAMD) network for blurred image restoration. The rationale is that through harnessing IMU data, we can determine the transformation of the camera pose during the image exposure phase, facilitating the deduction of the motion trajectory (aka. blur trajectory) for each point inside the three-dimensional space. Thus, the synthetic triplets using our strategy are inherently close to natural motion blur, strictly pixel-aligned, and mass-producible. Through comprehensive experiments, we demonstrate the advantages of the proposed framework: only two-pixel errors between our synthetic and real-world blur trajectories, a marked improvement (around 33.17%) of the state-of-the-art deblurring method MIMO on Peak Signal-to-Noise Ratio (PSNR).

cs.CV↗

arXiv2024

Data Trading and Monetization: Challenges and Open Research Directions

Traditional data monetization approaches face challenges related to data protection and logistics. In response, digital data marketplaces have emerged as intermediaries simplifying data transactions. Despite the growing establishment and acceptance of digital data marketplaces, significant challenges hinder efficient data trading. As a result, few companies can derive tangible value from their data, leading to missed opportunities in understanding customers, pricing decisions, and fraud prevention. In this paper, we explore both technical and organizational challenges affecting data monetization. Moreover, we identify areas in need of further research, aiming to expand the boundaries of current knowledge by emphasizing where research is currently limited or lacking.

cs.DC↗

arXiv2023

Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks

Skeleton Ground Truth (GT) is critical to the success of supervised skeleton extraction methods, especially with the popularity of deep learning techniques. Furthermore, we see skeleton GTs used not only for training skeleton detectors with Convolutional Neural Networks (CNN) but also for evaluating skeleton-related pruning and matching algorithms. However, most existing shape and image datasets suffer from the lack of skeleton GT and inconsistency of GT standards. As a result, it is difficult to evaluate and reproduce CNN-based skeleton detectors and algorithms on a fair basis. In this paper, we present a heuristic strategy for object skeleton GT extraction in binary shapes and natural images. Our strategy is built on an extended theory of diagnosticity hypothesis, which enables encoding human-in-the-loop GT extraction based on clues from the target's context, simplicity, and completeness. Using this strategy, we developed a tool, SkeView, to generate skeleton GT of 17 existing shape and image datasets. The GTs are then structurally evaluated with representative methods to build viable baselines for fair comparisons. Experiments demonstrate that GTs generated by our strategy yield promising quality with respect to standard consistency, and also provide a balance between simplicity and completeness.

cs.CV↗

arXiv2023

PADME-SoSci: A Platform for Analytics and Distributed Machine Learning for the Social Sciences

Data privacy and ownership are significant in social data science, raising legal and ethical concerns. Sharing and analyzing data is difficult when different parties own different parts of it. An approach to this challenge is to apply de-identification or anonymization techniques to the data before collecting it for analysis. However, this can reduce data utility and increase the risk of re-identification. To address these limitations, we present PADME, a distributed analytics tool that federates model implementation and training. PADME uses a federated approach where the model is implemented and deployed by all parties and visits each data location incrementally for training. This enables the analysis of data across locations while still allowing the model to be trained as if all data were in a single location. Training the model on data in its original location preserves data ownership. Furthermore, the results are not provided until the analysis is completed on all data locations to ensure privacy and avoid bias in the results.

cs.CR↗

arXiv2023

Deep Author Name Disambiguation using DBLP Data

In the academic world, the number of scientists grows every year and so does the number of authors sharing the same names. Consequently, it challenging to assign newly published papers to their respective authors. Therefore, Author Name Ambiguity (ANA) is considered a critical open problem in digital libraries. This paper proposes an Author Name Disambiguation (AND) approach that links author names to their real-world entities by leveraging their co-authors and domain of research. To this end, we use data collected from the DBLP repository that contains more than 5 million bibliographic records authored by around 2.6 million co-authors. Our approach first groups authors who share the same last names and same first name initials. The author within each group is identified by capturing the relation with his/her co-authors and area of research, represented by the titles of the validated publications of the corresponding author. To this end, we train a neural network model that learns from the representations of the co-authors and titles. We validated the effectiveness of our approach by conducting extensive experiments on a large dataset.

cs.DL↗

arXiv2023

Enhancing Data Space Semantic Interoperability through Machine Learning: a Visionary Perspective

Our vision paper outlines a plan to improve the future of semantic interoperability in data spaces through the application of machine learning. The use of data spaces, where data is exchanged among members in a self-regulated environment, is becoming increasingly popular. However, the current manual practices of managing metadata and vocabularies in these spaces are time-consuming, prone to errors, and may not meet the needs of all stakeholders. By leveraging the power of machine learning, we believe that semantic interoperability in data spaces can be significantly improved. This involves automatically generating and updating metadata, which results in a more flexible vocabulary that can accommodate the diverse terminologies used by different sub-communities. Our vision for the future of data spaces addresses the limitations of conventional data exchange and makes data more accessible and valuable for all members of the community.

cs.DB↗

arXiv2022

Whois? Deep Author Name Disambiguation using Bibliographic Data

As the number of authors is increasing exponentially over years, the number of authors sharing the same names is increasing proportionally. This makes it challenging to assign newly published papers to their adequate authors. Therefore, Author Name Ambiguity (ANA) is considered a critical open problem in digital libraries. This paper proposes an Author Name Disambiguation (AND) approach that links author names to their real-world entities by leveraging their co-authors and domain of research. To this end, we use a collection from the DBLP repository that contains more than 5 million bibliographic records authored by around 2.6 million co-authors. Our approach first groups authors who share the same last names and same first name initials. The author within each group is identified by capturing the relation with his/her co-authors and area of research, which is represented by the titles of the validated publications of the corresponding author. To this end, we train a neural network model that learns from the representations of the co-authors and titles. We validated the effectiveness of our approach by conducting extensive experiments on a large dataset.

cs.DL↗

arXiv2022

Hybrid Physics and Deep Learning Model for Interpretable Vehicle State Prediction

Physical motion models offer interpretable predictions for the motion of vehicles. However, some model parameters, such as those related to aero- and hydrodynamics, are expensive to measure and are often only roughly approximated reducing prediction accuracy. Recurrent neural networks achieve high prediction accuracy at low cost, as they can use cheap measurements collected during routine operation of the vehicle, but their results are hard to interpret. To precisely predict vehicle states without expensive measurements of physical parameters, we propose a hybrid approach combining deep learning and physical motion models including a novel two-phase training procedure. We achieve interpretability by restricting the output range of the deep neural network as part of the hybrid model, which limits the uncertainty introduced by the neural network to a known quantity. We have evaluated our approach for the use case of ship and quadcopter motion. The results show that our hybrid model can improve model interpretability with no decrease in accuracy compared to existing deep learning approaches.

cs.LG↗

arXiv2022

COIN: Counterfactual Image Generation for VQA Interpretation

Due to the significant advancement of Natural Language Processing and Computer Vision-based models, Visual Question Answering (VQA) systems are becoming more intelligent and advanced. However, they are still error-prone when dealing with relatively complex questions. Therefore, it is important to understand the behaviour of the VQA models before adopting their results. In this paper, we introduce an interpretability approach for VQA models by generating counterfactual images. Specifically, the generated image is supposed to have the minimal possible change to the original image and leads the VQA model to give a different answer. In addition, our approach ensures that the generated image is realistic. Since quantitative metrics cannot be employed to evaluate the interpretability of the model, we carried out a user study to assess different aspects of our approach. In addition to interpreting the result of VQA models on single images, the obtained results and the discussion provides an extensive explanation of VQA models' behaviour.

cs.CV↗

arXiv2021

Leveraging Commonsense Knowledge on Classifying False News and Determining Checkworthiness of Claims

Widespread and rapid dissemination of false news has made fact-checking an indispensable requirement. Given its time-consuming and labor-intensive nature, the task calls for an automated support to meet the demand. In this paper, we propose to leverage commonsense knowledge for the tasks of false news classification and check-worthy claim detection. Arguing that commonsense knowledge is a factor in human believability, we fine-tune the BERT language model with a commonsense question answering task and the aforementioned tasks in a multi-task learning environment. For predicting fine-grained false news types, we compare the proposed fine-tuned model's performance with the false news classification models on a public dataset as well as a newly collected dataset. We compare the model's performance with the single-task BERT model and a state-of-the-art check-worthy claim detection tool to evaluate the check-worthy claim detection. Our experimental analysis demonstrates that commonsense knowledge can improve performance in both tasks.

cs.CL↗

arXiv2021

Bib2Auth: Deep Learning Approach for Author Disambiguation using Bibliographic Data

Author name ambiguity remains a critical open problem in digital libraries due to synonymy and homonymy of names. In this paper, we propose a novel approach to link author names to their real-world entities by relying on their co-authorship pattern and area of research. Our supervised deep learning model identifies an author by capturing his/her relationship with his/her co-authors and area of research, which is represented by the titles and sources of the target author's publications. These attributes are encoded by their semantic and symbolic representations. To this end, Bib2Auth uses ~ 22K bibliographic records from the DBLP repository and is trained with each pair of co-authors. The extensive experiments have proved the capability of the approach to distinguish between authors sharing the same name and recognize authors with different name variations. Bib2Auth has shown good performance on a relatively large dataset, which qualifies it to be directly integrated into bibliographic indices.

cs.DL↗

arXiv2021

BiblioDAP: The 1st Workshop on Bibliographic Data Analysis and Processing

Automatic processing of bibliographic data becomes very important in digital libraries, data science and machine learning due to its importance in keeping pace with the significant increase of published papers every year from one side and to the inherent challenges from the other side. This processing has several aspects including but not limited to I) Automatic extraction of references from PDF documents, II) Building an accurate citation graph, III) Author name disambiguation, etc. Bibliographic data is heterogeneous by nature and occurs in both structured (e.g. citation graph) and unstructured (e.g. publications) formats. Therefore, it requires data science and machine learning techniques to be processed and analysed. Here we introduce BiblioDAP'21: The 1st Workshop on Bibliographic Data Analysis and Processing.

cs.DL↗