BBDC2Leonhard HennigFeb 23, 2021Go to Project SiteInformation ExtractionLeonhard HennigSenior ResearcherRelatedData4TransparencyText2TechBIFOLDCora4NLPPLASSPublicationsConsidering Likelihood in NLP Classification Explanations with Occlusion and Language ModelingRecently, state-of-the-art NLP models gained an increasing syntactic and semantic understanding of language, and explanation methods …David Harbecke, Christoph AltPDF Cite Project DOIProbing Linguistic Features of Sentence-Level Representations in Neural Relation ExtractionDespite the recent progress, little is known about the features captured by state-of-the-art neural relation extraction (RE) models. …Christoph Alt, Aleksandra Gabryszak, Leonhard HennigPDF Cite Code Project Project Project DOITACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction TaskTACRED is one of the largest, most widely used crowdsourced datasets in Relation Extraction (RE). But, even with recent advances in …Christoph Alt, Aleksandra Gabryszak, Leonhard HennigPDF Cite Code Project Project Project DOIEvaluating German Transformer Language Models with Syntactic Agreement TestsPre-trained transformer language models (TLMs) have recently refashioned natural language processing (NLP): Most stateof-the-art NLP …Karolina Zaczynska, Nils Feldhus, Robert Schwarzenberg, Aleksandra Gabryszak, Sebastian MöllerPDF Cite Project
