Filling Knowledge Gaps in a Broad-Coverage Machine Translation System

1995/06/10 by Kevin Knight, Knight, Kevin, Ishwar Chander +15
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling #cmp-lg #cs.CL

paper · pdf · doi:10.48550/arxiv.cmp-lg/9506009

7 pages, Compressed and uuencoded postscript. To appear: IJCAI-95

arxiv created 1995/06/10 · openalex publication_date 1995/06/10 · arxiv updated 2009/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Knowledge-based machine translation (KBMT) techniques yield high quality in domains 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 gaps, often using robust statistical techniques. We describe quantitative and qualitative results from JAPANGLOSS, a broad-coverage Japanese-English MT system.

Related

• Building a Large-Scale Knowledge Base for Machine Translation
• MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation
• KoBE: Knowledge-Based Machine Translation Evaluation
• Building Machine Translation Systems for the Next Thousand Languages
• Testing the Limits of Machine Translation from One Book