Paper: Semantic Roles for String to Tree Machine Translation

ACL ID P13-2074
Title Semantic Roles for String to Tree Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

We experiment with adding semantic role information to a string-to-tree machine translation system based on the rule ex- traction procedure of Galley et al. (2004). We compare methods based on augment- ing the set of nonterminals by adding se- mantic role labels, and altering the rule extraction process to produce a separate set of rules for each predicate that encom- pass its entire predicate-argument struc- ture. Our results demonstrate that the sec- ond approach is effective in increasing the quality of translations.