Cross-lingual Text Classification Using Topic-Dependent Word Probabilities.
Daniel AndradeKunihiko SadamasaAkihiro TamuraMasaaki TsuchidaPublished in: HLT-NAACL (2015)
Keyphrases
- cross lingual
- text classification
- n gram
- translation model
- parallel corpus
- word segmentation
- word sense
- topic modeling
- statistical machine translation
- language independent
- bag of words
- word alignment
- indian languages
- term frequency
- text categorization
- language modeling
- text mining
- latent topics
- machine translation system
- sentiment analysis
- cross lingual information retrieval
- sentiment classification
- out of vocabulary
- cross language
- co occurrence
- labeled data
- text documents
- machine learning
- feature selection
- text data
- sentence level
- knn
- bilingual dictionaries
- transfer learning
- topic models
- unlabeled data
- source language
- keywords
- semantic features
- machine translation
- parallel corpora
- news articles
- text corpora
- active learning