Fast BTG-Forest-Based Hierarchical Sub-sentential Alignment [article]

Hao Wang, Yves Lepage
2017 arXiv   pre-print
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.
arXiv:1711.07265v1 fatcat:wnao5ntu6vhs3b5uumsrsv4jpm