Filling Knowledge Gaps in a Broad-Coverage Machine Translation System
Filling Knowledge Gaps in a Broad-Coverage Machine Translation System
复制标题
填补广泛覆盖的机器翻译系统中的知识空白
DOI：
--
复制
发表时间：
1995
期刊：
影响因子：
--
通讯作者：
Kenji Yamada
中科院分区：
文献类型：
--
作者：
Kevin Knight;Ishwar Chander;Matthew Haines;V. Hatzivassiloglou;E. Hovy;Masayo Iida;Steve K. Luk;R. Whitney;Kenji Yamada
基于知识的机器翻译（Knowledge-based Machine Translation，KBMT）技术具有详细的语义模型、有限的词汇和受控的输入语法，在这些维度上的扩展意味着获得大量的知识资源，也意味着在确定性知识尚未可用时的合理行为。本文描述了如何填补各种KBMT知识缺口 *，经常使用强大的统计技术，我们描述了定量和定性的结果，从JAPANGLOSS，一个广泛覆盖的日本-英语MT系统。
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.