What Can We Get From 1000 Tokens? A Case Study of Multilingual POS Tagging For Resource-Poor Languages.
Long DuongTrevor CohnKarin VerspoorSteven BirdPaul CookPublished in: EMNLP (2014)
Keyphrases
- pos tagging
- machine translation
- language independent
- cross lingual
- pos taggers
- word segmentation
- target language
- language specific
- part of speech
- n gram
- chinese word segmentation
- source language
- domain adaptation
- cross language information retrieval
- cross language
- machine translation system
- dependency parsing
- statistical machine translation
- natural language
- sentiment classification
- query translation
- text classification
- natural language processing
- penn treebank
- word sense disambiguation
- information extraction
- digital libraries
- language modeling
- named entity recognition