Grammatisk merking av The Lancaster-Oslo/Bergen Corpus: ordklassebestemmelse ved hjelp av ordslutt (Grammatical marking of The Lancaster-Oslo/Bergen Corpus: Part-of-speech classification using word endings) [In Norwegian].
Mette-Cathrine JahrStig JohanssonPublished in: NODALIDA (1981)
Keyphrases
- part of speech
- training corpus
- unknown words
- pos tagging
- linguistic information
- text classification
- multiword
- noun phrases
- n gram
- word sense
- chinese word segmentation
- ambiguous words
- linguistic features
- penn treebank
- word sense disambiguation
- feature vectors
- pos taggers
- word segmentation
- syntactic information
- natural language processing
- syntactic categories
- lexical information
- machine learning
- tree bank
- sentence level
- parse tree
- image classification
- natural language text
- feature selection
- feature extraction
- natural language
- text documents
- bag of words
- wordnet
- dependency parsing
- syntactic features
- language model
- topic tracking
- co occurrence
- classification accuracy
- phrase structure
- training set
- semantic relations
- semantic roles
- statistical machine translation