Cost-Effective Information Extraction from Lists in OCRed Historical Documents.
Thomas L. PackerDavid W. EmbleyPublished in: HIP@ICDAR (2015)
Keyphrases
- cost effective
- historical documents
- information extraction
- handwriting recognition
- word recognition
- low cost
- cost effectiveness
- natural language processing
- document images
- text mining
- web documents
- historical manuscripts
- question answering
- information retrieval
- named entities
- extraction rules
- machine learning
- textual data
- text processing
- machine translation
- text documents
- speech recognition
- power system
- real time