Search Results for author: Pieter Fivez

Found 6 papers, 4 papers with code

Scalable Few-Shot Learning of Robust Biomedical Name Representations

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.

Continual Learning Few-Shot Learning

Integrating Higher-Level Semantics into Robust Biomedical Name Representations

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.

Mapping probability word problems to executable representations

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.

Contextualised Word Representations Probabilistic Programming +1

Conceptual Grounding Constraints for Truly Robust Biomedical Name Representations

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.

Unsupervised Context-Sensitive Spelling Correction of English and Dutch Clinical Free-Text with Word and Character N-Gram Embeddings

1 code implementation19 Oct 2017 Pieter Fivez, Simon Šuster, Walter Daelemans

We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings.

Spelling Correction

Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings

no code implementations WS 2017 Pieter Fivez, Simon {\v{S}}uster, Walter Daelemans

We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings.

Spelling Correction

Cannot find the paper you are looking for? You can Submit a new open access paper.