Semantic Roles for SMT: A Hybrid Two-Pass Model

Abstract

We present results on a novel hybrid semantic SMT model that incorporates the strengths of both semantic role labeling and phrase-based statistical machine translation. The approach avoids major complexity limitations via a two-pass architecture. The first pass is performed using a conventional phrase-based SMT model. The second pass is performed by a re-ordering strategy guided by shallow semantic parsers that produce both semantic frame and role labels. Evaluation on a Wall Street Journal newswire genre test set showed the hybrid model to yield an improvement of roughly half a point in BLEU score over a strong pure phrase-based SMT baseline – to our knowledge, the first successful application of semantic role labeling to SMT.

Extracted Key Phrases

1 Figure or Table

Statistics

01020200920102011201220132014201520162017
Citations per Year

94 Citations

Semantic Scholar estimates that this publication has 94 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Wu2009SemanticRF, title={Semantic Roles for SMT: A Hybrid Two-Pass Model}, author={Dekai Wu and Pascale Fung}, booktitle={HLT-NAACL}, year={2009} }