Induced lexico-syntactic patterns improve information extraction from online medical forums

OBJECTIVE: To reliably extract two entity types, symptoms and conditions (SCs), and drugs and treatments (DTs), from patient-authored text (PAT) by learning lexico-syntactic patterns from data annotated with seed dictionaries. BACKGROUND AND SIGNIFICANCE: Despite the increasing quantity of PAT (eg,...

Полное описание

Сохранить в:
Библиографические подробности
Главные авторы: Gupta, Sonal, MacLean, Diana L, Heer, Jeffrey, Manning, Christopher D
Формат: Artigo
Язык:Inglês
Опубликовано: BMJ Publishing Group 2014
Предметы:
Focus on Biomedical Natural Language Processing and Data Modeling
Online-ссылка:https://ncbi.nlm.nih.gov/pmc/articles/PMC4147618/
https://ncbi.nlm.nih.gov/pubmed/24970840
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1136/amiajnl-2014-002669
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!

Схожие документы