Evaluating word embeddings and a revised corpus for part-of-speech tagging in Portuguese.
Erick Rocha FonsecaJoão Luís Garcia RosaSandra M. AluísioPublished in: J. Braz. Comput. Soc. (2015)
Keyphrases
- noun phrases
- chinese word segmentation
- pos tagging
- word frequencies
- part of speech
- unknown words
- multiword
- sentence level
- text corpus
- english words
- word pairs
- word segmentation
- training corpus
- topic tracking
- morphological analysis
- named entities
- word sense
- statistical machine translation
- co occurrence
- n gram
- linguistic information
- lexical features
- natural language processing
- vector space
- semantic relations
- word sense disambiguation
- manifold learning
- translation model
- word recognition
- cross language
- dependency parsing
- natural language text
- word frequency
- parallel corpus
- euclidean space
- word co occurrence
- query translation
- anaphora resolution
- dimensionality reduction
- semantic similarity
- probabilistic model
- linguistic features
- query terms