Reranking Translation Hypotheses Using Structural Properties
Saša Hasan, Oliver Bender, Hermann Ney · RWTH Publications (RWTH Aachen) · 2006
We investigate methods that add syntactically motivated features to a statistical machine translation system in a reranking framework.The goal is to analyze whether shallow parsing techniques help in identifying ungrammatical hypotheses.We show that improvements are possible by utilizing supertagging, lightweight dependency analysis, a link grammar parser and a maximum-entropy based chunk parser.Adding features to n-best lists and discriminatively training the system on a development set increases the BLEU score up to 0.7% on the test set.