Probabilistic Unification-Based Integration Of Syntactic and Semantic Preferences For Nominal Compounds (1990)
| Citations: | 6 - 3 self |
BibTeX
@MISC{Wu90probabilisticunification-based,
author = {Dekai Wu},
title = {Probabilistic Unification-Based Integration Of Syntactic and Semantic Preferences For Nominal Compounds},
year = {1990}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
In thi paper, we describe a probabilistic framework for unification-based grammars that facilitates'integrating syntactic mid .'mantic constraints and preferences. We share many of the concerns found in recent work on massively-parallel language interpret 'ation models, although the proposal refleets our belief in the value of a higher-level account that is not stated in terms of dis- tributed 'computation. We also feel that inadequate learning heOries severely limit ex 'isting massively-parallel language interpre- tation models. A learning theory is not only interesting in its own right, but must underlie, any quantitative account of language interpretation, because the complexity of interaction between constraints and prefer- ences makes ad hoc trial-and-error strate- gies for picking numbers infeasible, particularly for semantics in realistically-sized do mains.
