Paper: Lattice Parsing to Integrate Speech Recognition and Rule-Based Machine Translation

ACL ID E09-1054
Title Lattice Parsing to Integrate Speech Recognition and Rule-Based Machine Translation
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2009
Authors

In this paper, we present a novel approach to integrate speech recognition and rule- based machine translation by lattice pars- ing. The presented approach is hybrid in two senses. First, it combines struc- tural and statistical methods for language modeling task. Second, it employs a chart parser which utilizes manually cre- ated syntax rules in addition to scores ob- tained after statistical processing during speech recognition. The employed chart parser is a unification-based active chart parser. It can parse word graphs by using a mixed strategy instead of being bottom-up or top-down only. The results are reported based on word error rate on the NIST HUB-1 word-lattices. The presented ap- proach is implemented and compared with other syntactic language modeling tech- niques.