https://puma.ub.uni-stuttgart.de/tag/AnalyticComputing%20@AnalyticComp%20dblpPUMA RSS feed for /tag/AnalyticComputing%20@AnalyticComp%20dblp2026-04-16T17:18:26+02:00https://puma.ub.uni-stuttgart.de/bibtex/22856acbb53ab24e90ed0b6ec382dd519/lschmelzeisenlschmelzeisen2020-11-26T10:19:52+01:00@AnalyticComp AnalyticComputing dblp myown <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Aidan Hogan" itemprop="url" href="/person/1937ebb9057ebdd6fa997a18741b79755/author/0"><span itemprop="name">A. Hogan</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Eva Blomqvist" itemprop="url" href="/person/1937ebb9057ebdd6fa997a18741b79755/author/1"><span itemprop="name">E. Blomqvist</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Michael Cochez" itemprop="url" href="/person/1937ebb9057ebdd6fa997a18741b79755/author/2"><span itemprop="name">M. Cochez</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Claudia d&#039;Amato" itemprop="url" href="/person/1937ebb9057ebdd6fa997a18741b79755/author/3"><span itemprop="name">C. d&#039;Amato</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Gerard de Melo" itemprop="url" href="/person/1937ebb9057ebdd6fa997a18741b79755/author/4"><span itemprop="name">G. de Melo</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Claudio Gutierrez" itemprop="url" href="/person/1937ebb9057ebdd6fa997a18741b79755/author/5"><span itemprop="name">C. Gutierrez</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="José Emilio Labra Gayo" itemprop="url" href="/person/1937ebb9057ebdd6fa997a18741b79755/author/6"><span itemprop="name">J. Gayo</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Sabrina Kirrane" itemprop="url" href="/person/1937ebb9057ebdd6fa997a18741b79755/author/7"><span itemprop="name">S. Kirrane</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Sebastian Neumaier" itemprop="url" href="/person/1937ebb9057ebdd6fa997a18741b79755/author/8"><span itemprop="name">S. Neumaier</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Axel Polleres" itemprop="url" href="/person/1937ebb9057ebdd6fa997a18741b79755/author/9"><span itemprop="name">A. Polleres</span></a></span></span> and 8 other author(s). </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">CoRR</span>, </em> </span>(<em><span>March 2020<meta content="March 2020" itemprop="datePublished"/></span></em>)</span>Thu Nov 26 10:19:52 CET 2020CoRRmarKnowledge Graphsabs/2003.023202020@AnalyticComp AnalyticComputing dblp myown In this paper we provide a comprehensive introduction to knowledge graphs, which have recently garnered significant attention from both industry and academia in scenarios that require exploiting diverse, dynamic, large-scale collections of data. After a general introduction, we motivate and contrast various graph-based data models and query languages that are used for knowledge graphs. We discuss the roles of schema, identity, and context in knowledge graphs. We explain how knowledge can be represented and extracted using a combination of deductive and inductive techniques. We summarise methods for the creation, enrichment, quality assessment, refinement, and publication of knowledge graphs. We provide an overview of prominent open knowledge graphs and enterprise knowledge graphs, their applications, and how they use the aforementioned techniques. We conclude with high-level future research directions for knowledge graphs.https://puma.ub.uni-stuttgart.de/bibtex/2f7dbf0a622ff3e694c009ec93060c47f/lschmelzeisenlschmelzeisen2020-11-26T10:09:22+01:00@AnalyticComp AnalyticComputing dblp myown <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Lukas Schmelzeisen" itemprop="url" href="/person/161c25eacd5f7a0ba141e22543fe91a8e/author/0"><span itemprop="name">L. Schmelzeisen</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Steffen Staab" itemprop="url" href="/person/161c25eacd5f7a0ba141e22543fe91a8e/author/1"><span itemprop="name">S. Staab</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">CoRR</span>, </em> </span>(<em><span>January 2019<meta content="January 2019" itemprop="datePublished"/></span></em>)</span>Thu Nov 26 10:09:22 CET 2020CoRRjanLearning Taxonomies of Concepts and not Words using Contextualized Word Representations: A Position Paper.abs/1902.021692019@AnalyticComp AnalyticComputing dblp myown Taxonomies are semantic hierarchies of concepts. One limitation of current taxonomy learning systems is that they define concepts as single words. This position paper argues that contextualized word representations, which recently achieved state-of-the-art results on many competitive NLP tasks, are a promising method to address this limitation. We outline a novel approach for taxonomy learning that (1) defines concepts as synsets, (2) learns density-based approximations of contextualized word representations, and (3) can measure similarity and hypernymy among them. https://puma.ub.uni-stuttgart.de/bibtex/2b05149be0c2e6b80ac4e4d2ab3dfd193/lschmelzeisenlschmelzeisen2020-11-26T10:05:00+01:00@AnalyticComp AnalyticComputing dblp myown <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Ipek Baris" itemprop="url" href="/person/18ecf60543c716db98189eb98c772be4f/author/0"><span itemprop="name">I. Baris</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Lukas Schmelzeisen" itemprop="url" href="/person/18ecf60543c716db98189eb98c772be4f/author/1"><span itemprop="name">L. Schmelzeisen</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Steffen Staab" itemprop="url" href="/person/18ecf60543c716db98189eb98c772be4f/author/2"><span itemprop="name">S. Staab</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/PublicationIssue" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="journal">CoRR</span>, </em> </span>(<em><span>April 2019<meta content="April 2019" itemprop="datePublished"/></span></em>)</span>Thu Nov 26 10:05:00 CET 2020CoRRaprCLEARumor at SemEval-2019 Task 7: ConvoLving ELMo Against Rumors.abs/1904.030842019@AnalyticComp AnalyticComputing dblp myown This paper describes our submission to SemEval-2019 Task 7: RumourEval: Determining Rumor Veracity and Support for Rumors. We participated in both subtasks. The goal of subtask A is to classify the type of interaction between a rumorous social media post and a reply post as support, query, deny, or comment. The goal of subtask B is to predict the veracity of a given rumor. For subtask A, we implement a CNN-based neural architecture using ELMo embeddings of post text combined with auxiliary features and achieve a F1-score of 44.6%. For subtask B, we employ a MLP neural network leveraging our estimates for subtask A and achieve a F1-score of 30.1% (second place in the competition). We provide results and analysis of our system performance and present ablation experiments.https://puma.ub.uni-stuttgart.de/bibtex/242f0d00808b61a6cc0a7d69aa701b464/lschmelzeisenlschmelzeisen2020-11-26T10:00:37+01:00@AnalyticComp AnalyticComputing dblp myown <span data-person-type="author" class="authorEditorList "><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Ipek Baris" itemprop="url" href="/person/18ecf60543c716db98189eb98c772be4f/author/0"><span itemprop="name">I. Baris</span></a></span>, </span><span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Lukas Schmelzeisen" itemprop="url" href="/person/18ecf60543c716db98189eb98c772be4f/author/1"><span itemprop="name">L. Schmelzeisen</span></a></span>, </span> and <span><span itemtype="http://schema.org/Person" itemscope="itemscope" itemprop="author"><a title="Steffen Staab" itemprop="url" href="/person/18ecf60543c716db98189eb98c772be4f/author/2"><span itemprop="name">S. Staab</span></a></span></span>. </span><span class="additional-entrytype-information"><span itemtype="http://schema.org/Book" itemscope="itemscope" itemprop="isPartOf"><em><span itemprop="name">SemEval@NAACL-HLT</span>, </em></span><em>page <span itemprop="pagination">1105-1109</span>. </em><em><span itemprop="publisher">Association for Computational Linguistics</span>, </em>(<em><span>June 2019<meta content="June 2019" itemprop="datePublished"/></span></em>)</span>Thu Nov 26 10:00:37 CET 2020SemEval@NAACL-HLTconf/semeval/2019jun1105-1109CLEARumor at SemEval-2019 Task 7: ConvoLving ELMo Against Rumors.2019@AnalyticComp AnalyticComputing dblp myown This paper describes our submission to SemEval-2019 Task 7: RumourEval: Determining Rumor Veracity and Support for Rumors. We participated in both subtasks. The goal of subtask A is to classify the type of interaction between a rumorous social media post and a reply post as support, query, deny, or comment. The goal of subtask B is to predict the veracity of a given rumor. For subtask A, we implement a CNN-based neural architecture using ELMo embeddings of post text combined with auxiliary features and achieve a F1-score of 44.6%. For subtask B, we employ a MLP neural network leveraging our estimates for subtask A and achieve a F1-score of 30.1% (second place in the competition). We provide results and analysis of our system performance and present ablation experiments.