Grouping conversational markers across languages by exploiting large comparable corpora and unsupervised segmentation.
Laurent PrévotMatthieu StaliShu-Chuan TsengPublished in: BUCC@LREC (2018)
Keyphrases
- comparable corpora
- unsupervised segmentation
- cross language information retrieval
- parallel corpora
- news articles
- machine translation
- textured images
- segmentation algorithm
- language modeling
- text corpora
- cross lingual
- word pairs
- linguistic resources
- image segmentation
- bilingual dictionaries
- query translation
- text documents
- language independent
- cross language
- object recognition
- natural language
- labor intensive
- target language
- machine learning
- texture features
- text classification
- information retrieval