Exploring Semantic Word Representations for Recognition-Free NLP on Handwritten Document Images.
Oliver TüselmannGernot A. FinkPublished in: ICDAR (4) (2023)
Keyphrases
- handwritten document images
- historical documents
- handwriting recognition
- handwritten documents
- word spotting
- word segmentation
- historical manuscripts
- optical character recognition
- word recognition
- natural language
- document analysis
- document image retrieval
- natural language processing
- image preprocessing
- character recognition
- printed documents
- text processing
- document collections
- document images
- speech recognition
- information extraction
- word level
- document image analysis
- feature extraction
- text analysis
- object recognition
- n gram
- word sense disambiguation
- text documents
- feature selection
- keywords
- text mining
- handwritten text
- language model
- wordnet
- semantic features
- machine translation
- text retrieval
- semantic similarity
- recognition algorithm
- language modeling
- dynamic time warping
- language independent