English

Integrating Knowledge Bases and Statistics in MT

cmp-lg 2008-02-03 v1 Computation and Language

Abstract

We summarize recent machine translation (MT) research at the Information Sciences Institute of USC, and we describe its application to the development of a Japanese-English newspaper MT system. Our work aims at scaling up grammar-based, knowledge-based MT techniques. This scale-up involves the use of statistical methods, both in acquiring effective knowledge resources and in making reasonable linguistic choices in the face of knowledge gaps.

Keywords

Cite

@article{arxiv.cmp-lg/9409001,
  title  = {Integrating Knowledge Bases and Statistics in MT},
  author = {Kevin Knight and Ishwar Chander and Matthew Haines and Vasileios Hatzivassiloglou and Eduard Hovy and Masayo Iida and Steve K. Luk and Akitoshi Okumura and Richard Whitney and Kenji Yamada},
  journal= {arXiv preprint arXiv:cmp-lg/9409001},
  year   = {2008}
}

Comments

8 pages, compressed, uuencoded postscript