The ambiguity of negation in natural language queries to information retrieval systems
✍ Scribed by McQuire, April R. ;Eastman, Caroline M.
- Publisher
- John Wiley and Sons
- Year
- 1998
- Tongue
- English
- Weight
- 202 KB
- Volume
- 49
- Category
- Article
- ISSN
- 0002-8231
No coin nor oath required. For personal study only.
✦ Synopsis
In the next section, we provide an overview of the guage queries to information retrieval systems is preproblems presented by the use of negation in queries. We sented. Whenever a query that has negation is entered, then present the results of a survey used to investigate the system will determine whether or not it is necessary the interpretation of negation in queries; this survey shows for the user to clarify exactly what constituents in the substantial disagreement in interpretation and thus serious query are being negated. If clarification is needed, the user is presented with a list of choices and asked to potential problems with the ambiguity of negation. An select the appropriate one. The algorithm used is based algorithm is then proposed to handle negation through a on the results of a survey administered to 64 subjects. clarification dialog; a prototype implementation is de-The subjects were given a number of queries using negascribed. We conclude by describing some possible future tion. For each query, several possible choices for the work. negated constituent(s) were given. Whenever a lexical unit composed of nouns connected by the conjunction and was negated, there was general agreement on the response. But whenever there were multiple lexical units The Problem of Negation in Queries involved, such as complex lexical units connected by and or prepositional phrases, the subjects were divided Negation is exceedingly difficult to implement in natuon the choices. The results of this survey indicate that ral language processing systems. It is not always clear it is not possible for a system to automatically disambiguate all uses of negation. However, it is possible for the what constituent or constituents are being negated. An user interface to handle disambiguation through a clariadditional problem is presented when handling queries to fication dialog during which a user is asked to select information retrieval systems. Even when the appropriate from a list of possible interpretations.