<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Avishek Das</style></author><author><style face="normal" font="default" size="100%">Abhilekha Dalal</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Hidden Neuron Activation Analysis on Labeled Text Data</style></title><secondary-title><style face="normal" font="default" size="100%">K-CAP '25: Knowledge Capture Conference 2025</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Concept-based Explanation</style></keyword><keyword><style  face="normal" font="default" size="100%">Dense Layer Analysis</style></keyword><keyword><style  face="normal" font="default" size="100%">Explainable AI</style></keyword><keyword><style  face="normal" font="default" size="100%">Hidden Neuron Analysis</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2025</style></year><pub-dates><date><style  face="normal" font="default" size="100%">12/2025</style></date></pub-dates></dates><publisher><style face="normal" font="default" size="100%">ACM</style></publisher><pub-location><style face="normal" font="default" size="100%">USA</style></pub-location><pages><style face="normal" font="default" size="100%">206 - 210</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Understanding the internal mechanisms of deep neural networks remains a central challenge in the field of Explainable Artificial Intelligence (XAI). With the rapid advancement of neural architectures in natural language processing (NLP), analyzing the role of hidden neurons in capturing and processing linguistic features has become increasingly important. This study investigates Hidden Neuron Activation Analysis on labeled text data to reveal how individual neurons contribute to a model’s decision-making process. We propose a model-agnostic explainability framework for text classifiers that identifies concepts activating specific neurons involved in classification. An LSTM-based network is trained on the AG News topic classification dataset, comprising four distinct classes, and the final Dense layer with 64 neurons was analyzed. In addition, statistical analyses like the Mann-Whitney U Test is conducted to assess the robustness and reliability of the system. The statistical analysis shows that, concepts plays important role in the decision making process of neural network. Our findings enhance interpretability in NLP models and offer a foundation for optimizing neural architectures in text classification tasks.&lt;/p&gt;
</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>27</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Joseph Zalewski</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author><author><style face="normal" font="default" size="100%">Krzysztof Janowicz</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Semantic Compression with Region Calculi in Nested Hierarchical Grids (Technical Report)</style></title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Hierarchical Grids</style></keyword><keyword><style  face="normal" font="default" size="100%">Knowledge Graphs</style></keyword><keyword><style  face="normal" font="default" size="100%">RCC5</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2021</style></year></dates><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;We propose the combining of region connection calculi with nested hierarchical grids for representing spatial region data in the context of knowledge graphs, thereby avoiding reliance on vector representations. We present a resulting region calculus, and provide qualitative and formal evidence that this representation can be favorable with large data volumes in the context of knowledge graphs; in particular we study means of efficiently choosing which triples to store to minimize space requirements when data is represented this way, and we provide an algorithm for finding the smallest possible set of triples for this purpose including an asymptotic measure of the size of this set for a special case. We prove that a known constraint calculus is adequate for the reconstruction of all triples describing a region from such a pruned representation, but problematic for reasoning with hierarchical grids in general.&lt;/p&gt;
</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Cogan Shimizu</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author><author><style face="normal" font="default" size="100%">Quinn Hirt</style></author><author><style face="normal" font="default" size="100%">Dean Rehberger</style></author><author><style face="normal" font="default" size="100%">Seila Gonzalez Estrecha</style></author><author><style face="normal" font="default" size="100%">Catherine Foley</style></author><author><style face="normal" font="default" size="100%">Alicia M. Sheill</style></author><author><style face="normal" font="default" size="100%">Walter Hawthorne</style></author><author><style face="normal" font="default" size="100%">Jeff Mixter</style></author><author><style face="normal" font="default" size="100%">Ethan Watrall</style></author><author><style face="normal" font="default" size="100%">Ryan Carty</style></author><author><style face="normal" font="default" size="100%">Duncan Tarr</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">The Enslaved Ontology: Peoples of the Historic Slave Trade</style></title><secondary-title><style face="normal" font="default" size="100%">Journal of Web Semantics</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">data integration</style></keyword><keyword><style  face="normal" font="default" size="100%">digital humanities</style></keyword><keyword><style  face="normal" font="default" size="100%">history of the slave trade</style></keyword><keyword><style  face="normal" font="default" size="100%">modular ontology</style></keyword><keyword><style  face="normal" font="default" size="100%">Ontology Design Patterns</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2020</style></year><pub-dates><date><style  face="normal" font="default" size="100%">08/2020</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">63</style></volume><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;We present the Enslaved Ontology (V1.0) which was developed for integrating data about the historic slave trade from diverse sources in a use case driven by historians. Ontology development followed modular ontology design principles as derived from ontology design pattern application best practices and the eXtreme Design Methodology. Ontology content focuses on data about historic persons and the event records from which this data can be taken. It also incorporates provenance modeling and some temporal and spatial aspects. The ontology is available as serialized in the Web Ontology Language OWL, and carries modularization annotations using the Ontology Pattern Language (OPLa). It is available under the Creative Commons CC BY 4.0 license.&lt;/p&gt;
</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Amir Hossein Yazdavar</style></author><author><style face="normal" font="default" size="100%">Mohammad Saeid Mahdavinejad</style></author><author><style face="normal" font="default" size="100%">Goonmeet Baja</style></author><author><style face="normal" font="default" size="100%">William Romine</style></author><author><style face="normal" font="default" size="100%">Amit Sheth</style></author><author><style face="normal" font="default" size="100%">Amir Hassan Monadjemi</style></author><author><style face="normal" font="default" size="100%">Krishnaprasad Thirunarayan</style></author><author><style face="normal" font="default" size="100%">John M. Meddar</style></author><author><style face="normal" font="default" size="100%">Annie Myers</style></author><author><style face="normal" font="default" size="100%">Jyotishman Pathak</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Multimodal mental health analysis in social media</style></title><secondary-title><style face="normal" font="default" size="100%">PLoS ONE</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Explainable Machine Learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Hypothesis Testing</style></keyword><keyword><style  face="normal" font="default" size="100%">National Language Processing</style></keyword><keyword><style  face="normal" font="default" size="100%">Prediction</style></keyword><keyword><style  face="normal" font="default" size="100%">Regression</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2020</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0226248&amp;type=printable</style></url></web-urls></urls><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;p.p1 {margin: 0.0px 0.0px 0.0px 0.0px; font: 9.5px Helvetica}&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;Depression is a major public health concern in the U.S. and globally. While successful early&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;identification and treatment can lead to many positive health and behavioral outcomes,&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;depression, remains undiagnosed, untreated or undertreated due to several reasons,&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;including denial of the illness as well as cultural and social stigma. With the ubiquity of social&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;media platforms, millions of people are now sharing their online persona by expressing their&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;thoughts, moods, emotions, and even their daily struggles with mental health on social&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;media. Unlike traditional observational cohort studies conducted through questionnaires&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;and self-reported surveys, we explore the reliable detection of depressive symptoms from&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;tweets obtained, unobtrusively. Particularly, we examine and exploit multimodal big (social)&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;data to discern depressive behaviors using a wide variety of features including individuallevel&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;demographics. By developing a multimodal framework and employing statistical techniques&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;to fuse heterogeneous sets of features obtained through the processing of visual,&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;textual, and user interaction data, we significantly enhance the current state-of-the-art&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;approaches for identifying depressed individuals on Twitter (improving the average F1-&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;Score by 5 percent) as well as facilitate demographic inferences from social media. Besides&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;providing insights into the relationship between demographics and mental health, our&lt;/p&gt;

&lt;p class=&quot;p1&quot;&gt;research assists in the design of a new breed of demographic-aware health interventions.&lt;/p&gt;
</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">David Carral</style></author><author><style face="normal" font="default" size="100%">Adila Krisnadhi</style></author><author><style face="normal" font="default" size="100%">Sebastian Rudolph</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author></authors><secondary-authors><author><style face="normal" font="default" size="100%">C. Maria Keet</style></author><author><style face="normal" font="default" size="100%">Valentina A. M. Tamma</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">All But Not Nothing: Left-Hand Side Universals for Tractable OWL Profiles</style></title><secondary-title><style face="normal" font="default" size="100%">Proceedings of the 11th International Workshop on OWL: Experiences and Directions (OWLED 2014) co-located with 13th International Semantic Web Conference on (ISWC 2014), Riva del Garda, Italy, October 17-18, 2014.</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">description logics</style></keyword><keyword><style  face="normal" font="default" size="100%">Horn Logics</style></keyword><keyword><style  face="normal" font="default" size="100%">OWL</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2014</style></year><pub-dates><date><style  face="normal" font="default" size="100%">10/2014</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://ceur-ws.org/Vol-1265/owled2014_submission_13.pdf</style></url></web-urls></urls><publisher><style face="normal" font="default" size="100%">CEUR-WS.org</style></publisher><volume><style face="normal" font="default" size="100%">1265</style></volume><pages><style face="normal" font="default" size="100%">97-108</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">We show that occurrences of the universal quantifier in the left-hand side of general concept inclusions can be rewritten into EL++ axioms under certain circumstances. I.e., this intuitive modeling feature is available for OWL EL while retaining tractability. Furthermore, this rewriting makes it possible to reason over corresponding extensions of EL++ and Horn-SROIQ using standard reasoners.</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Markus Krötzsch</style></author><author><style face="normal" font="default" size="100%">Sebastian Rudolph</style></author><author><style face="normal" font="default" size="100%">Pascal Hitzler</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Complexities of Horn Description Logics</style></title><secondary-title><style face="normal" font="default" size="100%">ACM Trans. Comput. Log.</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">computational complexity</style></keyword><keyword><style  face="normal" font="default" size="100%">description logics</style></keyword><keyword><style  face="normal" font="default" size="100%">Horn logic</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2013</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://doi.acm.org/10.1145/2422085.2422087</style></url></web-urls></urls><volume><style face="normal" font="default" size="100%">14</style></volume><pages><style face="normal" font="default" size="100%">2</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">Description Logics (DLs) have become a prominent paradigm for representing knowledge bases in a variety of application areas. Central to leveraging them for corresponding systems is the provision of a favourable balance between expressivity of the knowledge representation formalism on the one hand, and runtime performance of reasoning algorithms on the other. Due to this, Horn description logics (Horn DLs) have attracted attention since their (worst-case) data complexities are in general lower than their overall (i.e. combined) complexities, which makes them attractive for reasoning with large sets of instance data (ABoxes). However, the natural question whether Horn DLs also provide advantages for schema (TBox) reasoning has hardly been addressed so far. In this paper, we therefore provide a thorough and comprehensive analysis of the combined complexities of Horn DLs. While the combined complexity for many Horn DLs studied herein turns out to be the same as for their non-Horn counterparts, we identify subboolean DLs where Hornness simplifies reasoning. We also provide convenient normal forms for Horn DLs.</style></abstract></record></records></xml>