This paper presents the semantic analysis of queries written in natural language (French) and dedicated to the object oriented data bases. The studied queries include one or two nominal groups (NG) articulating around a verb. A NG consists of one or several keywords (application dependent noun or value). Simple semantic filters are defined for iden-tifying these keywords which can be of semantic value: class, simple attribute, composed attribute, key value or not key value. Coherence rules and coherence constraints are introduced, to check the validity of the co-occurrence of two consecutive nouns in complex NG. If a query is constituted of a single NG, no further analysis is required. Otherwise, if a query covers two valid NG, it is a subject of studying the semantic coherence of the verb and both NG which are at-tached to it.

©Copyright in this paper belongs to the author(s) Published in collaboration with the

Korean natural language queries are composed of a number of basic building blocks. This paper describes the process to identify the basic patterns considered to be basic building blocks constructing Korean queries. Two sets of Korean queries generated by two groups of senior-level students were experimented. Questions from the first set were produced by students who had no knowledge about databases and schema. Students from the second group attended a short lecture and understood that the Korean queries would be executed by a computer. By analyzing these experimental queries, seven basic patterns are identified. Korean queries combined by these basic patterns cover more than 80% of all questions. 1 Introduction Recently a number of Korean natural language query interfaces which transform Korean queries into formal database queries such as QUEL or SQL have been developed. NHI (Kim and Lee, 1985) accepts Korean natural language queries and generates QUEL. K-NLQ (Chae...

A natural language query interface for databases provides the user friendliness in retrieving the desired information by querying in a native natural language. Up to now, many natural language query interfaces for conventional databases have been developed. However, the field of natural language query interfaces for object-oriented databases which have recently started to emerge as the next-generation databases has become a new research area. This paper describes a processing technique to manipulate natural language representations of path expressions. From the fact that the path expression is one of the key features in the object-oriented data model, a frame-based decomposition method is proposed for efficient processing. 1 Introduction The objective of natural language interfaces is to take inputs in human language and extract from them something which is meaningful to a computer. A natural language query interface to a database system provides end users with a way to formulate que...