P. McFetridge and C. Groeneboer. Novel Terms and Coordination in a Natural Language Interface. In Knowledge Based Computer Systems. S. Ramani, R. Chandrasekar and K.S.R. Anjaneyulu (eds.), Springer, Berlin, 1990.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....is the processing of database values as part of the user query. As especially systems that claim to be domain independent do not access the knowledge contained in the database for use in natural language analysis, the usual approach is to assume that undefined words represent database values (see [21]) Therefore, if one considers the possibility of misspelled values, those systems are not able to distinguish between new database values for insertion or update and misspelled existent data. The very first database interface LUNAR [38] as well as the first commercially available natural ....

P. McFetridge and C. Groeneboer. Novel Terms and Coordination in a Natural Language Interface. In Knowledge Based Computer Systems. S. Ramani, R. Chandrasekar and K.S.R. Anjaneyulu (eds.), Springer, Berlin, 1990.

.... [Copestake90, Androutsopoulos94] The reason for this are the many limitations which still exist and which are caused by two main factors: missing customization, resulting in unexpected restrictions, and missing integration, responsible for insufficient performance and wrong interpretation (see [McFetridge90, Sparck Jones94] Another important reason why many previous attempts to build successful systems failed can be seen in the fact that the characteristics of natural language interfaces in contrast to other fields of natural language processing were neglected: specific application domains with ....

....correction are only applied if the prior semantic analysis could not produce a unique representation. This is especially important with regard to the latter in order to be able to distinguish correctly between misspelled existent values and new database values for insert or update operations (see [McFetridge90] 3.1. Language specific issues One of the most obvious difficulties for natural language analysis of Japanese is of course the writing system which consists of a mixture of the three different sub systems Hiragana, Katakana, and Kanji. Whereas the first two are syllable writings, the latter ....

P. McFetridge, C. Groeneboer. Novel Terms and Coordination in a Natural Language Interface. S. Rhamani, R. Chandrasekar, K.S.R. Anjaneyulu (eds). Knowledge Based Computer Systems. Springer, Berlin, 1990.

.... and that are due to two main factors: missing customisation, resulting in unexpected Information Systems and Technologies for Network Society, Fukuoka, Japan, September 1997 restrictions, and missing integration, which is responsible for insufficient performance and wrong interpretations (see [18, 22]) Regarding the former we stress the importance of empirically collecting the training and test data. With that, we obtain realistic input sentences that cover all relevant linguistic phenomena and guarantee wide user acceptance in later actual use. Only recently considerable research effort has ....

McFetridge, P., Groeneboer, C.: Novel terms and coordination in a natural language interface. Rhamani, S., Chandrasekar, R., Anjaneyulu, K. S. R. (eds): Knowledge Based Computer Systems. Springer-Verlag, Berlin (1990)

....is the processing of database values as part of the user query. As especially systems that claim to be domain independent do not access the knowledge contained in the database for use in natural language analysis, the usual approach is to assume that undefined words represent database values (see [17]) Therefore, if one considers the possibility of misspelled values, those systems are not able to distinguish between new database values for insertion or update and misspelled existent data. Deductive databases incorporate the power to solve these shortcomings, therefore we propose the ....

P. McFetridge, C. Groeneboer. Novel Terms and Coordination in a Natural Language Interface. S. Ramani, R. Chandrasekar, K.S.R. Anjaneyulu (eds). Knowledge Based Computer Systems., Springer, Berlin, 1990.

.... use (for a good recent survey see [1] The reason for this are the many still existing limitations which are caused by two main factors: missing customization, resulting in unexpected restrictions, and missing integration, responsible for insufficient performance and wrong interpretation [10]. As concerns the former we stress the importance of empirically collecting the training and test data so that the system can be based on realistic input data to cover all relevant linguistic constructs. With regard to missing integration we adapt the Integrated Deductive Approach [15] by ....

McFetridge, P., Groeneboer, C.: Novel Terms and Coordination in a Natural Language Interface. Rhamani, S., Chandrasekar, R., Anjaneyulu, K.S.R. (eds): Knowledge Based Computer Systems. Springer, Berlin (1990)

.... (for a good recent survey see [1] The reason for this are the many limitations which still exist and which are caused by two main factors: missing customization, resulting in unexpected restrictions, and missing integration, responsible for insufficient performance and wrong interpretation (see [14]) As concerns missing customization we stress the importance of empirically collecting the training and test data so that realistic input sentences are obtained which cover all relevant linguistic phenomena and guarantee wide user acceptance in later practical use. Only recently considerable ....

McFetridge, P., Groeneboer, C.: Novel Terms and Coordination in a Natural Language Interface. Rhamani, S., Chandrasekar, R., Anjaneyulu, K.S.R. (eds): Knowledge Based Computer Systems. Springer, Berlin (1990)

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC