paper-with-me

홈 › Papers

Fast BTG-Forest-Based Hierarchical Sub-sentential Alignment

2017-11-20 · Hao Wang, Yves Lepage

In this paper, we propose a novel BTG-forest-based alignment method. Based on a fast unsupervised initialization of parameters using variational IBM models, we synchronously parse parallel sentences top-down and align hierarchically under the constraint of BTG. Our two-step method can achieve the same run-time and comparable translation performance as fast_align while it yields smaller phrase tables. Final SMT results show that our method even outperforms in the experiment of distantly related languages, e.g., English-Japanese.

📄 PDF Abstract BibTeX arXiv:1711.07265

Code (0)

등록된 구현이 없습니다.

Tasks

Translation

Similar Papers 제목 키워드 기반

Combining fast\_align with Hierarchical Sub-sentential Alignment for Better Word Alignments

2016-12-01 · WS 2016 12 · Hao Wang, Yves Lepage

fast align is a simple and fast word alignment tool which is widely used in state-of-the-art machine translation systems. It yields comparable results in the end-to-end translation experiments of various language pairs. …

Machine TranslationTranslationWord Alignment

Sampling-based Alignment and Hierarchical Sub-sentential Alignment in Chinese--Japanese Translation of Patents

2015-10-01 · WS 2015 10 · Wei Yang, Zhongwen Zhao, Baosong Yang, Yves Lepage
Machine TranslationTranslation

Yet Another Symmetrical and Real-time Word Alignment Method: Hierarchical Sub-sentential Alignment using F-measure

2016-10-01 · PACLIC 2016 10 · Hao Wang, Yves Lepage
Machine TranslationWord Alignment

Alignement sous-phrastique hi\'erarchique avec Anymalign (Hierarchical Sub-Sentential Alignment with Anymalign) [in French]

2012-06-01 · JEPTALNRECITAL 2012 6 · Adrien Lardilleux, Fran{\c{c}}ois Yvon, Yves Lepage
Machine Translation

Forest-Guided Semantic Transport for Label-Supervised Manifold Alignment

2026-02-01 · Adrien Aumon, Myriam Lizotte, Guy Wolf, Kevin R. Moon 외 arxiv

Label-supervised manifold alignment bridges the gap between unsupervised and correspondence-based paradigms by leveraging shared label information to align multimodal datasets. Still, most existing methods rely on Euclid…