Pre-Trained Word Embedding and Language Model Improve Multimodal Machine Translation: A Case Study in Multi30K.
Tosho HirasawaMasahiro KanekoAizhan ImankulovaMamoru KomachiPublished in: IEEE Access (2022)
Keyphrases
- statistical machine translation
- machine translation
- language model
- n gram
- translation model
- cross lingual
- language independent
- language modeling
- cross language information retrieval
- out of vocabulary
- word sense disambiguation
- machine translation system
- word alignment
- chinese english
- word level
- natural language processing
- information retrieval
- probabilistic model
- information extraction
- target language
- context sensitive
- retrieval model
- document retrieval
- speech recognition
- multiword
- source language
- natural language
- machine learning
- query expansion
- text classification
- vector space
- word segmentation
- bag of words
- test collection
- bilingual dictionaries
- co occurrence
- ad hoc information retrieval