FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation.
Wenhao ZhuShujian HuangTong PuPingxuan HuangXu ZhangJian YuWei ChenYanfeng WangJiajun ChenPublished in: LREC (2022)
Keyphrases
- fine grained
- machine translation
- domain adaptation
- pos tagging
- cross lingual
- sentiment classification
- semi supervised
- natural language processing
- cross domain
- multiple sources
- access control
- labeled data
- test data
- transfer learning
- word sense disambiguation
- information extraction
- target language
- target domain
- document classification
- natural language
- semi supervised learning
- text mining
- knowledge base
- unlabeled data
- unsupervised learning
- xml documents
- source language
- database systems