Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Vitalii, Zhelezniak"'
Autor:
Francesco, Moramarco, Damir, Juric, Aleksandar, Savkov, Jack, Flann, Maria, Lehl, Kristian, Boda, Tessa, Grafen, Vitalii, Zhelezniak, Sunir, Gohil, Alex Papadopoulos, Korfiatis, Nils, Hammerla
Publikováno v:
AMIA Annu Symp Proc
Clinical notes are an efficient way to record patient information but are notoriously hard to decipher for non-experts. Automatically simplifying medical text can empower patients with valuable information about their health, while saving clinicians
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::499193d8b979732d94f205beb2475d32
https://pubmed.ncbi.nlm.nih.gov/35308976
https://pubmed.ncbi.nlm.nih.gov/35308976
Publikováno v:
ACL
Word embedding-based similarity measures are currently among the top-performing methods on unsupervised semantic textual similarity (STS) tasks. Recent work has increasingly adopted a statistical view on these embeddings, with some of the top approac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8c53422e1b2373f7b9095dc6fb086fb
https://doi.org/10.18653/v1/2020.acl-main.741
https://doi.org/10.18653/v1/2020.acl-main.741
Publikováno v:
EMNLP/IJCNLP (1)
Similarity measures based purely on word embeddings are comfortably competing with much more sophisticated deep learning and expert-engineered systems on unsupervised semantic textual similarity (STS) tasks. In contrast to commonly used geometric app
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8196c927878a7a044de32e679a635fd8
http://arxiv.org/abs/1910.02902
http://arxiv.org/abs/1910.02902
Publikováno v:
NAACL-HLT (1)
A large body of research into semantic textual similarity has focused on constructing state-of-the-art embeddings using sophisticated modelling, careful choice of learning signals and many clever tricks. By contrast, little attention has been devoted
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8dcb1f7264476e83aeff8c6f23ae2dd6