Machine Translation Using Abductive Inference
Abstract
Machine Translation and World Knowledge. Many existing approaches to machine translation take for granted that the information presented in the output is found somewhere in the input, and, moreover, that such information should be expressed at a single representational level, say, in terms of the parse trees or of semantic assertions. Languages, however, not only express the equivalent information by drastically different linguistic means, but also often disagree in what distinctions should be expressed linguistically at all. For example, in translating from Japanese to English, it is often necessary to suppy determiners for noun phrases, and this in general cannot be done without deep understanding of the source text. Similarly, intranslating from English to Japanese, politeness considerations, which in English are implicit in the social situation and explicit in very diffuse ways in, for example, the heavy use of hypotheticals, must be realized grammatically in Japanese. Machine translation therefore requires that the appropriate inferences be drawn and that the text be interpreted to some depth.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1990
- Accession Number
- ADA259458
Entities
People
- Jerry R. Hobbs
- Megumi Kameyama
Organizations
- SRI International