BERT for Long Documents: A Case Study of Automated ICD Coding.
Arash AfkanpourShabir AdeelHansenclever BassaniArkady EpshteynHongbo FanIsaac JonesMahan MalihiAdrian NauthRaj SinhaSanjana WoonnaShiva ZamaniElli KanalMikhail FomitchevDonny CheungPublished in: LOUHI@EMNLP (2022)
Keyphrases
- free text
- information retrieval systems
- coding scheme
- information retrieval
- document collections
- web documents
- metadata
- case study
- xml documents
- semi automated
- fully automated
- metadata extraction
- digital documents
- document clustering
- document classification
- patient records
- document retrieval
- text documents
- relevant documents
- latent semantic analysis
- coding method
- medical records
- document content
- test bed
- structured documents
- legal documents
- document analysis
- similarity measure
- query terms
- text mining
- electronic documents
- bit rate
- ranked list