Training a Parser for Machine Translation Reordering

We propose a simple training regime that can improve the extrinsic performance of a parser, given only a corpus of sentences and a way to automatically evaluate the extrinsic quality of a candidate parse. We apply our method to train parsers that excel when used as part of a reordering component in a statistical machine translation system. We use a corpus of weakly-labeled reference reorderings to guide parser training. Our best parsers contribute significant improvements in subjective translation quality while their intrinsic attachment scores typically regress.

• Type: Journal
• Year: 2011
• Where: EMNLP
• Authors: Jason Katz-Brown, Slav Petrov, Ryan T. McDonald, Franz Josef Och, David Talbot, Hiroshi Ichikawa, Masakazu Seno, Hideto Kazawa
• Keywords: EMNLP 2011, Machine Translation System, Natural Language Processing, Statistical Machine Translation, Translation Quality