Using Corpus Statistics to Evaluate Nonce Words.
Özkan KiliçPublished in: ESSLLI Student Sessions (2013)
Keyphrases
- english words
- word frequencies
- multiword
- word pairs
- unknown words
- text corpus
- training corpus
- text corpora
- noun phrases
- spontaneous speech
- word sense
- word frequency
- n gram
- linguistic information
- related words
- natural language text
- person names
- test set
- parallel corpus
- word sense disambiguation
- textual features
- text documents
- pos tagging
- conversational speech
- annotated corpus
- descriptive statistics
- manually annotated
- word co occurrence
- keywords
- document level
- stop words
- word recognition
- text classification