CSLI Publications logo
new books
catalog
series
contact us
for authors
order
search
CSLI Publications
Facebook
 

Song, Sanghoun & Bender, Emily M.: Using Information Structure to Improve Transfer-based MT

This paper hypothesizes that transfer-based machine translation systems can be improved by encoding information structure in both the source and target grammars, and preserving information structure in the transfer stage. We explore how information structure can be represented within the HPSG/MRS formalism (Pollard and Sag, 1994; Copestake et al., 2005) and how it can help refine multilingual MT. Building upon that framework, we provide a sample translation between English and Japanese and check the feasibility of the proposals in small-scale translation systems built with the HPSG/MRS-based LOGON MT infrastructure (Oepen et al., 2007). Our experiment shows the information structure-based MT system that we propose in this paper reduces the number of translations 75.71% for Japanese and 80.23% for Korean. The dramatic reductions in the number of translations is expected to make a contribution to our HPSG/MRS-based MT in terms of latency as well as accuracy.


Maintained by Stefan Müller

Created: November 16, 2011
Last modified: January 09, 2019

pubs @ csli.stanford.edu