Roman Jurowetzki

Hamid Bekamiri, Daniel S. Hain, Roman Jurowetzki

Patent data is an important source of knowledge for innovation research, while the technological similarity between pairs of patents is a key enabling indicator for patent analysis. Recently researchers have been using patent vector space models based on different NLP embeddings models to calculate the technological similarity between pairs of patents to help better understand innovations, patent landscaping, technology mapping, and patent quality evaluation. More often than not, Text Embedding is a vital precursor to patent analysis tasks. A pertinent question then arises: How should we measure and evaluate the accuracy of these embeddings? To the best of our knowledge, there is no comprehensive survey that builds a clear delineation of embedding models' performance for calculating patent similarity indicators. Therefore, in this study, we provide an overview of the accuracy of these algorithms based on patent classification performance and propose a standard library and dataset for assessing the accuracy of embeddings models based on PatentSBERTa approach. In a detailed discussion, we report the performance of the top 3 algorithms at section, class, and subclass levels. The results based on the first claim of patents show that PatentSBERTa, Bert-for-patents, and TF-IDF Weighted Word Embeddings have the best accuracy for computing sentence embeddings at the subclass level. According to the first results, the performance of the models in different classes varies, which shows researchers in patent analysis can utilize the results of this study to choose the best proper model based on the specific section of patent data they used.

Richard A. A. Jonker, Alexander Christiansen, Alexandros Maniatis et al.

This paper presents the joint participation of the BIT.UA and AAUBS groups in the ArchEHR-QA 2026 shared task, which focuses on clinical question answering and evidence grounding in a low-resource setting. Due to the absence of training data and the strict data privacy constraints inherent to the healthcare domain (e.g. GDPR), we investigate the capabilities of Large Language Models (LLMs) without weight updates. We evaluate several state-of-the-art proprietary models and locally deployable open-source alternatives using various prompt engineering strategies, including task decomposition, Chain-of-Thought, and in-context learning. Furthermore, we explore majority voting and LLM-as-a-judge ensembling techniques to maximize predictive robustness. Our results demonstrate that while proprietary models exhibit strong resilience to prompt variations, domain-adapted open-source models (such as MedGemma 3 27B) achieve highly competitive performance when paired with the right prompt. Overall, our prompt-based approach proved highly effective, securing 1st place in Subtask 4 (evidence citation alignment) and 3rd place in Subtask 3 (patient-friendly answer generation). All code, results, and prompts are available on our GitHub repository: https://github.com/bioinformatics-ua/ArchEHR-QA-2026.

Hamid Bekamiri, Daniel S. Hain, Roman Jurowetzki

This study provides an efficient approach for using text data to calculate patent-to-patent (p2p) technological similarity, and presents a hybrid framework for leveraging the resulting p2p similarity for applications such as semantic search and automated patent classification. We create embeddings using Sentence-BERT (SBERT) based on patent claims. We leverage SBERTs efficiency in creating embedding distance measures to map p2p similarity in large sets of patent data. We deploy our framework for classification with a simple Nearest Neighbors (KNN) model that predicts Cooperative Patent Classification (CPC) of a patent based on the class assignment of the K patents with the highest p2p similarity. We thereby validate that the p2p similarity captures their technological features in terms of CPC overlap, and at the same demonstrate the usefulness of this approach for automatic patent classification based on text data. Furthermore, the presented classification framework is simple and the results easy to interpret and evaluate by end-users. In the out-of-sample model validation, we are able to perform a multi-label prediction of all assigned CPC classes on the subclass (663) level on 1,492,294 patents with an accuracy of 54% and F1 score > 66%, which suggests that our model outperforms the current state-of-the-art in text-based multi-label and multi-class patent classification. We furthermore discuss the applicability of the presented framework for semantic IP search, patent landscaping, and technology intelligence. We finally point towards a future research agenda for leveraging multi-source patent embeddings, their appropriateness across applications, as well as to improve and validate patent embeddings by creating domain-expert curated Semantic Textual Similarity (STS) benchmark datasets.

Daniel Hain, Roman Jurowetzki

Recent years have seen a substantial development of quantitative methods, mostly led by the computer science community with the goal of developing better machine learning applications, mainly focused on predictive modeling. However, economic, management, and technology forecasting research has so far been hesitant to apply predictive modeling techniques and workflows. In this paper, we introduce a machine learning (ML) approach to quantitative analysis geared towards optimizing the predictive performance, contrasting it with standard practices inferential statistics, which focus on producing good parameter estimates. We discuss the potential synergies between the two fields against the backdrop of this, at first glance, target-incompatibility. We discuss fundamental concepts in predictive modeling, such as out-of-sample model validation, variable and model selection, generalization, and hyperparameter tuning procedures. We are providing a hands-on predictive modeling introduction for a quantitative social science audience while aiming at demystifying computer science jargon. We use the illustrative example of patent quality estimation - which should be a familiar topic of interest in the Scientometrics community - guiding the reader through various model classes and procedures for data pre-processing, modeling, and validation. We start off with more familiar easy to interpret model classes (Logit and Elastic Nets), continues with less familiar non-parametric approaches (Classification Trees, Random Forest, Gradient Boosted Trees), and finally presents artificial neural network architectures, first a simple feed-forward and then a deep autoencoder geared towards rare-event prediction.