1 code implementation • RepL4NLP (ACL) 2022 • Ioannis Dikeoulias, Saadullah Amin, Günter Neumann
Temporal knowledge graph completion (TKGC) has become a popular approach for reasoning over the event and temporal knowledge graphs, targeting the completion of knowledge with accurate but missing information.
Knowledge Graph Embedding Temporal Knowledge Graph Completion +1
1 code implementation • BioNLP (ACL) 2022 • Saadullah Amin, Noon Pokaratsiri Goldstein, Morgan Kelly Wixted, Alejandro García-Rudolph, Catalina Martínez-Costa, Günter Neumann
Despite the advances in digital healthcare systems offering curated structured knowledge, much of the critical information still lies in large volumes of unlabeled and unstructured clinical texts.
1 code implementation • COLING 2022 • Saadullah Amin, Pasquale Minervini, David Chang, Pontus Stenetorp, Günter Neumann
Relation extraction in the biomedical domain is challenging due to the lack of labeled data and high annotation costs, needing domain experts.
1 code implementation • ICML 2020 • Saadullah Amin, Stalin Varanasi, Katherine Ann Dunfield, Günter Neumann
Bilinear models, while expressive, are prone to overfitting and lead to quadratic growth of parameters in number of relations.
1 code implementation • WS 2020 • Saadullah Amin, Katherine Ann Dunfield, Anna Vechkaeva, Günter Neumann
Fact triples are a common form of structured knowledge used within the biomedical domain.
no code implementations • 19 Apr 2018 • Tyler Renslow, Günter Neumann
We present LightRel, a lightweight and fast relation classifier.
no code implementations • WS 2018 • Georg Heigold, Günter Neumann, Josef van Genabith
In this paper, we study the impact of noisy input.