Abstract
This chapter discusses how to determine the relation that holds between nouns in a noun sequence. For natural language understanding, a system must be able to discover, for example, that there is a Locative relation in “vegetable market” but not in “lemon peel,” which contains, rather, a Part-of relation. A system is described here that will determine these relations automatically. First a classification of possible relations is presented, formulated as wh-questions. Since there is only a limited number of these relations that can possibly hold in a noun sequence, the system considers each possible relation in turn and provides an indication of how likely the relation is between two nouns by evaluating the semantic properties of each of the two nouns as evidenced by information extracted from online dictionaries. The result is the most likely interpretation of the noun sequence, together with the most likely senses of each noun.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Kluwer Academic Publishers
About this chapter
Cite this chapter
Vanderwende, L. (1993). SENS: The System for Evaluating Noun Sequences. In: Jensen, K., Heidorn, G.E., Richardson, S.D. (eds) Natural Language Processing: The PLNLP Approach. The Kluwer International Series in Engineering and Computer Science, vol 196. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-3170-8_13
Download citation
DOI: https://doi.org/10.1007/978-1-4615-3170-8_13
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-7923-9279-8
Online ISBN: 978-1-4615-3170-8
eBook Packages: Springer Book Archive