Akamon: An Open Source Toolkit for Tree/Forest-Based Statistical Machine Translation

Xianchao Wu, Takuya Matsuzaki, Jun'ichi Tsujii

Abstract: We describe Akamon, an open source toolkit for tree and forest-based statistical machine translation (Liu et al., 2006; Mi et al., 2008; Mi and Huang, 2008). Akamon implements all of the algorithms required for tree/forest-to-string decoding using tree-to-string translation rules: multiple-thread forest-based decoding, n-gram language model integration, beam- and cube-pruning, k-best hypotheses extraction, and minimum error rate training. In terms of tree-to-string translation rule extraction, the toolkit implements the traditional maximum likelihood algorithm using PCFG trees (Galley et al., 2004) and HPSG trees/forests (Wu et al., 2010).