: NLP Vocabulary: hierarchical phrase-based machine translation

applied NLP > machine translation > data-driven machine translation > statistical machine translation > hierarchical phrase-based machine translation

hierarchical phrase-based machine translation

A statistical machine translation approach that extends the phrase-based model by introducing a hierarchical structure to the translation process. HPMT segments the source sentence into phrases and groups them into nodes arranged in a hierarchical structure, allowing for more accurate translations of complex sentences.

Hierarchical phrase-based machine translation can capture global reordering with synchronous context-free grammar but has little ability to evaluate the correctness of word orderings during decoding. (Hayashi, Tsukada, Sudoh, Duh & Yamamoto, 2010)
The hierarchical phrase-based machine translation (aka hiero) extends the phrase-based models notion of phrase from naive contiguous words to a sequence of words and sub-phrases (Chiang 2005). (Tan, 2016)
There has been much effort to improve performance for hierarchical phrase-based machine translation by employing linguistic knowledge. (Liu, Zhao, Wang & Cao, 2011)
Zhou et al. (2017) combined phrasebased statistical machine translation (PBMT) hi-erarchical phrase-based statistical machine translation (HPMT) and NMT with a unified architecture similar to the dominant NMT model. (Geng, Feng, Qin & Liu, 2018)

http://data.loterre.fr/ark:/67375/8LP-NPCKB3JG-5

RDF/XML TURTLE JSON-LD Last modified 4/29/24

Loterre