UdS-(retrain|distributional|surface): Improving POS Tagging for OOV Words in German CMC and Web Data.
Jakob PrangeAndrea HorbachStefan ThaterPublished in: WAC@ACL (2016)
Keyphrases
- web data
- pos tagging
- word segmentation
- out of vocabulary
- part of speech
- web mining
- machine translation
- dependency parsing
- semi structured
- n gram
- web content
- web documents
- word sense disambiguation
- co occurrence
- web pages
- pos taggers
- language independent
- cross lingual
- target language
- text classification
- cross language information retrieval
- query logs
- named entities
- document analysis
- natural language processing
- natural language
- artificial intelligence