Towards the Machine Reading of Arabic Calligraphy: A Letters Dataset and Corresponding Corpus of Text.
Seetah ALSalamahRoss D. KingPublished in: ASAR (2018)
Keyphrases
- arabic text
- broad coverage
- arabic language
- open domain
- text data
- supervised machine learning
- reading comprehension
- plain text
- natural language text
- recognizing textual entailment
- text corpus
- english words
- topic segmentation
- document corpus
- newspaper articles
- text retrieval
- lexical features
- keywords
- text corpora
- free text
- text collections
- named entity disambiguation
- text mining
- multiword
- unknown words
- sentence level
- writing style
- noun phrases
- scene text
- text documents
- spontaneous speech
- morphological analysis
- chinese characters
- syntactic features
- manually annotated
- language identification
- printed text
- information retrieval
- training corpus
- linguistic information