SelfSeg: A Self-supervised Sub-word Segmentation Method for Neural Machine Translation.
Haiyue SongRaj DabreChenhui ChuSadao KurohashiEiichiro SumitaPublished in: ACM Trans. Asian Low Resour. Lang. Inf. Process. (2023)
Keyphrases
- segmentation method
- machine translation
- word sense disambiguation
- statistical machine translation
- word level
- word alignment
- machine translation system
- target language
- parallel corpus
- language independent
- natural language processing
- image segmentation
- cross lingual
- english chinese
- active contours
- tasks in natural language processing
- language processing
- segmentation algorithm
- source language
- information extraction
- energy function
- grammar induction
- statistical translation models
- natural language
- natural language generation
- cross language information retrieval
- bilingual dictionaries
- chinese english
- conditional random fields
- bilingual lexicon
- parallel corpora
- target word
- word order
- word segmentation
- co occurrence
- pos tagging
- segmented images
- language resources
- query translation
- translation model
- artificial intelligence