Étiquetage en parties du discours de langues peu dotées par spécialisation des plongements lexicaux (POS tagging for low-resource languages by adapting word embeddings ).
Pierre MagistryAnne-Laure LigozatSophie RossetPublished in: CORIA-TALN-RJC (TALN) (2018)
Keyphrases
- pos taggers
- pos tagging
- chinese word segmentation
- word segmentation
- target language
- part of speech
- language independent
- machine translation
- source language
- word sense disambiguation
- n gram
- domain adaptation
- dependency parsing
- natural language processing
- cross lingual
- named entity recognition
- artificial intelligence
- text classification
- statistical machine translation
- noun phrases
- parse tree
- word pairs
- machine learning
- word order
- vector space
- low dimensional
- co occurrence
- named entities