no code implementations • EMNLP 2021 • Simon Suster, Pieter Fivez, Pietro Totis, Angelika Kimmig, Jesse Davis, Luc De Raedt, Walter Daelemans
While solving math word problems automatically has received considerable attention in the NLP community, few works have addressed probability word problems specifically.
no code implementations • NAACL (BioNLP) 2021 • Madhumita Sushil, Simon Suster, Walter Daelemans
We explore whether state-of-the-art BERT models encode sufficient domain knowledge to correctly perform domain-specific inference.
no code implementations • NAACL (BioNLP) 2021 • Madhumita Sushil, Simon Suster, Walter Daelemans
For evaluation of explanations, we create a synthetic sepsis-identification dataset, as well as apply our technique on additional clinical and sentiment analysis datasets.
1 code implementation • EACL 2021 • Pieter Fivez, Simon Suster, Walter Daelemans
Effective representation of biomedical names for downstream NLP tasks requires the encoding of both lexical as well as domain-specific semantic information.
1 code implementation • EACL (Louhi) 2021 • Pieter Fivez, Simon Suster, Walter Daelemans
It has not yet been empirically confirmed that training biomedical name encoders on fine-grained distinctions automatically leads to bottom-up encoding of such higher-level semantics.
1 code implementation • NAACL (BioNLP) 2021 • Pieter Fivez, Simon Suster, Walter Daelemans
Recent research on robust representations of biomedical names has focused on modeling large amounts of fine-grained conceptual distinctions using complex neural encoders.