Learning Bilingual Semantic Frames: Shallow Semantic Parsing vs. Semantic Role Projection

To explore the potential application of semantic roles in structural machine translation, we propose to study the automatic learning of English-Chinese bilingual predicate argument structure mapping. We describe ARG ALIGN, a new model for learning bilingual semantic frames that employs monolingual Chinese and English semantic parsers to learn bilingual semantic role mappings with 72.45% Fscore, given an unannotated parallel corpus. We show that, contrary to a common preconception, our ARG ALIGN model is superior to a semantic role projection model, SYN ALIGN, which reaches only a 46.63% F-score by assuming semantic parallelism in bilingual sentences. We present experimental data explaining that this is due to crosslingual mismatches between argument structures in English and Chinese at 17.24% of the time. This suggests that, in any potential application to enhance machine translation with semantic structural mapping, it may be preferable to employ independent automatic semantic parsers on source and target languages, rather than assuming semantic role parallelism.