SVALA: Annotation of Second-Language Learner Text Based on Mostly Automatic Alignment of Parallel Corpora.
Mats WirénArild MatssonDan RosénElena VolodinaPublished in: CLARIN Annual Conference (2018)
Keyphrases
- parallel corpora
- labor intensive
- parallel texts
- sentence pairs
- fully automated
- semi automatic
- error prone
- machine translation
- cross language information retrieval
- multimedia
- fully automatic
- machine translation system
- metadata
- active learning
- context sensitive
- knowledge base
- cross lingual
- image classification
- statistical machine translation
- word alignment