Filling Knowledge Gaps in a Broad-Coverage Machine Translation System
Abstract
Knowledge-based machine translation (KBMT) techniques yield high quabty in domuoH with detailed semantic models, limited vocabulary, and controlled input grammar Scaling up along these dimensions means acquiring large knowledge resources It also means behaving reasonably when definitive knowledge is not yet available This paper describes how we can fill various KBMT knowledge gap*, often using robust statistical techniques We describe quantitative and qualitative results from JAPANGLOSS, a broad-coverage Japanese-English MT system.
Cite
Text
Knight et al. "Filling Knowledge Gaps in a Broad-Coverage Machine Translation System." International Joint Conference on Artificial Intelligence, 1995.Markdown
[Knight et al. "Filling Knowledge Gaps in a Broad-Coverage Machine Translation System." International Joint Conference on Artificial Intelligence, 1995.](https://mlanthology.org/ijcai/1995/knight1995ijcai-filling/)BibTeX
@inproceedings{knight1995ijcai-filling,
title = {{Filling Knowledge Gaps in a Broad-Coverage Machine Translation System}},
author = {Knight, Kevin and Chander, Ishwar and Haines, Matthew and Hatzivassiloglou, Vasileios and Hovy, Eduard H. and Iida, Masayo and Luk, Steve K. and Whitney, Richard and Yamada, Kenji},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {1995},
pages = {1390-1397},
url = {https://mlanthology.org/ijcai/1995/knight1995ijcai-filling/}
}