Computer Science
8 years ago

Automated post-editor boosts statistical machine translation accuracy without linguistic tools.

Lecture notes in computer science
Automatic Post-Editing Method Using Translation Knowledge Based on Intuitive Common Parts Continuum for Statistical Machine Translation
Hiroshi Echizen‐ya, Kenji Araki, Yuzu Uchida, Eduard Hovy

Paper Summary

Related papers

Theme background image
Computer Science
3 years ago

Phrase-based machine translation boosts Chinese-English translation accuracy by over 30%, revolutionizing real-time language processing.

Type-2 Fuzzy Logic
Theme background image
Computer Science
8 years ago

Statistical machine translation boosts English-to-Tamil translation accuracy with parallel corpus and language modeling techniques.

Learning with Noisy Labels
Type-2 Fuzzy Logic
Neural Networks
Theme background image
Computer Science
8 years ago

Hybrid machine translation outperforms rule-based and statistical approaches, unlocking new levels of accuracy and fluency.

Machine Translation

A new method for improving machine translation has been developed. This method automatically learns translation rules from a large set of translated texts, without needing special language tools. These rules help match the overall structure of a sentence in one language to its translation in another language. By applying these rules to machine-translated text, better translations can be produced. Tests show that using these rules significantly improves the quality of machine translations.