An LDA-k-Means section selector and a BiLSTM-CRF NER model extract pharmaceutical manufacturing data from patents, with kappa 91.1% for section selection and micro-F1 84.2% for entity recognition.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Natural Language Processing tools for Pharmaceutical Manufacturing Information Extraction from Patents
An LDA-k-Means section selector and a BiLSTM-CRF NER model extract pharmaceutical manufacturing data from patents, with kappa 91.1% for section selection and micro-F1 84.2% for entity recognition.