Learn Before
Concept
Statistical Machine Translation vs Neural Machine Translation
SMT
- Phrase-based statistical approach.
- Store several meanings of particular word in advance.
- When the user enters input value, it divides it into the word. or phrase unit.
- Find and translate the most statistically similar meaning.
NMT
- How human brain trains itself.
- Applies a large artificial neural network
- Takes up less memory, less time
- NMT models fit a single model rather than a pipeline of fine-tuned models.
- Currently achieves comparably precise translation results.
- End-to-End model design
0
1
Updated 2021-08-05
Tags
Data Science
Related
Application of autoregressive generation given a prefix: Machine translation
Statistical Machine Translation vs Neural Machine Translation
Backtranslation
MT Evaluation
MT Corpora
Assessing Translation Effectiveness for a Specific Use Case
A company is developing a translation service for legal documents, where preserving the precise meaning and complex sentence structure of the original text is the highest priority. The company has access to a massive parallel corpus of legal texts. Given these requirements, which approach would be more suitable and why?
Evaluating Machine Translation Quality
Unaligned Data in Sequence Learning