Dork, B.J.; Garman, J.; Weinberg, A.: From syntactic encodings to thematic roles : building lexical entries for interlingual MT (1994/95)
0.00
0.0012620769 = product of:
0.0075724614 = sum of:
0.0075724614 = weight(_text_:in in 4074) [ClassicSimilarity], result of:
0.0075724614 = score(doc=4074,freq=4.0), product of:
0.059380736 = queryWeight, product of:
1.3602545 = idf(docFreq=30841, maxDocs=44218)
0.043654136 = queryNorm
0.12752387 = fieldWeight in 4074, product of:
2.0 = tf(freq=4.0), with freq of:
4.0 = termFreq=4.0
1.3602545 = idf(docFreq=30841, maxDocs=44218)
0.046875 = fieldNorm(doc=4074)
0.16666667 = coord(1/6)
- Abstract
- Aims to construct large scale lexicons for interlingual machine translation of English, Arabic, Korean, and Spanish. Describes techniques that predict salient linguistic features of a non English word using the features of its English gloss in a bilingual dictionary. While not exact, owing to inexact glosses and language to language variations, these techniques can augment an existing dictionary with reasonable accuracy, thus savionf significant time. Conducts 2 experiments that demonstrate the value of these techniques. The 1st tests the feasibility of building a database of thematic grids for over 6500 Arabic verbs based on a mapping between English glosses and the syntactic codes in Longman's Dictionary of Contemporary English. The 2nd experiment tested the automatic classification of verbs into a richer semantic typology from which a more refined set of thematic grids derived. While human intervention will always be necessary for the construction of a semantic classification from LODOCE such intervention is significantly minimized as more knowledge about the syntax semantics relation is introduced
