no code implementations • 15 Dec 2022 • Gizem Sogancioglu, Heysem Kaya
We use contextual and non-contextual embeddings that are trained on domain-independent as well as clinical domain-specific data.
no code implementations • 2 Aug 2022 • Gizem Sogancioglu, Fabian Mijsters, Amar van Uden, Jelle Peperzak
Clinical word embeddings are extensively used in various Bio-NLP problems as a state-of-the-art feature vector representation.
1 code implementation • 22 Jul 2022 • Francisca Pessanha, Gizem Sogancioglu
We propose an informed baseline to help disentangle the various contextual factors of influence in this type of case studies.
no code implementations • Bioinformatics 2017 • Gizem Sogancioglu, Hakime Öztürk, Arzucan Özgür
A benchmark data set consisting of 100 sentence pairs from the biomedical literature is manually annotated by five human experts and used for evaluating the proposed methods.
Ranked #8 on Sentence Embeddings For Biomedical Texts on BIOSSES (using extra training data)