Two-Step Machine Translation with Lattices
The idea of two-step machine translation was introduced to divide the complexity of the search space into two independent steps: (1) lexical translation and reordering, and (2) conjugation and declination in the target language. In this paper, we extend the two-step machine translation structure by replacing state-of-the-art phrase-based machine translation with the hierarchical machine translation in the 1st step. We further extend the fixed string-based input format of the 2nd step with word lattices (Dyer et al., 2008); this provides the 2nd step with the opportunity to choose among a sample of possible reorderings instead of relying on the single best one as produced by the 1st step.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModellingLemmatizationMachine TranslationTranslationVocal Bursts Valence PredictionSimilar Papers 제목 키워드 기반
Phrase Model Training for Statistical Machine Translation with Word Lattices of Preprocessing Alternatives
Neural Lattice Search for Domain Adaptation in Machine Translation
Domain adaptation is a major challenge for neural machine translation (NMT). Given unknown words or new domains, NMT systems tend to generate fluent translations at the expense of adequacy. We present a stack-based latti…
Domain AdaptationMachine TranslationNMTTranslationSyntactically Guided Neural Machine Translation
We investigate the use of hierarchical phrase-based SMT lattices in end-to-end neural machine translation (NMT). Weight pushing transforms the Hiero scores for complete translation hypotheses, with the full translation g…
DecoderLanguage ModelingLanguage ModellingMachine Translation+2Data Compression using Rank-1 Lattices for Parameter Estimation in Machine Learning
The mean squared error and regularized versions of it are standard loss functions in supervised machine learning. However, calculating these losses for large data sets can be computationally demanding. Modifying an appro…
Data Compressionparameter estimation