Detection of Difficult for Understanding Medical Words using Deep Learning

Pylieva, Hanna

Домівка
→
Students Research & Project Works | Роботи студентів
→
Факультет прикладних наук
→
Освітня програма наук про дані
→
2019
→
Перегляд матеріалів

dc.contributor.author	Pylieva, Hanna
dc.date.accessioned	2019-02-19T15:49:34Z
dc.date.available	2019-02-19T15:49:34Z
dc.date.issued	2019
dc.identifier.citation	Pylieva, Hanna. Detection of Difficult for Understanding Medical Words using Deep Learning : Master Thesis : manuscript / Hanna Pylieva ; Supervisor Artem Chernodub, Ph. D.; Ukrainian Catholic University, Department of Computer Sciences. – Lviv : [s.n.], 2019. – 42 p. : ill.	uk
dc.identifier.uri	http://er.ucu.edu.ua/handle/1/1336
dc.language.iso	en	uk
dc.subject	Medical Words	uk
dc.subject	Medical Understandability Text Embeddings	uk
dc.subject	Deep Learning	uk
dc.title	Detection of Difficult for Understanding Medical Words using Deep Learning	uk
dc.type	Preprint	uk
dc.status	Публікується вперше	uk
dc.description.abstracten	In the medical domain, non-specialized users often require a better understanding of medical information provided by doctors. In this work, we address this need. We introduce novel embeddings received from RNN - FrnnMUTE (French RNN Medical Understandability Text Embeddings) - and show how they help to improve identification of readability and understandability of medical words when applied as features in the classification task, reaching at maximum 87.0 F1 score. We also found out that adding pre-trained FastText word embeddings to the feature set substantially improves the performance of the classification model. For generalizability study of different models, we introduce a methodology comprising three crossvalidation scenarios which allow testing classifiers in real-world conditions: when understanding of medical words by new users is unknown or when no information about understandability of new words is provided for the model.	uk