Natural Language Database Interface for the Community Based Monitoring System

Natural Language Database Interface for the Community Based Monitoring System* Krissanne Kaye Garcia, Ma. Angelica Lumain, Jose Antonio Wong, Jhovee Gerard Yap, Charibeth Cheng De La Salle University – Manila. 1410 Taft Avenue Malate, Manila {10533834, 10517197, 10514848, 10506349, koc}@dlsu.edu.ph Abstract. In most information systems, databases are accessed and manipulated typically through systems developed to tailor-fit the company’s needs. The usual problem in these cases is the limitation on data accessibility because the users are constrained to the forms created for the system. Another way of accessing the database is through Structured Query Language (SQL), a language that is not familiar to end users, thus still limiting the access to the data. Natural Language Database Interfaces were developed to address limited database accessibility for end users. This paper presents AlLaDIn, a web-based natural language interface to the Community-Based Monitoring System of a city in the Philippines. Keywords: natural language database interface, SQL, CBMS, natural language query 1. Introduction CBMS is a poverty monitoring system that is now used in Pasay City. It tracks poverty by surveying the people living in a certain area. Once this is done, they input them using the programs Census Professional (CSPro) and CMS-Natural Resource Database (NRDB), which are customized free software used to encode the data and to digitize spot maps. The output of CSPro is a text file, which is then used as an input to the program STATA, which they use to actually statistically monitor poverty. Since STATA needs technical skills to be used effectively, the data is very hard to access. Thus, people who actually must have direct access to these pieces of information must first ask the people/person who are/is capable of using the software to get the data for them, which might take some time. To address this problem, a Natural Language Database Interface (NLDBI) was developed for CBMS that will allow users to access the CBMS data without having to learn STATA. A NLDBI allows users to access a database using natural language query. It accepts a user query, extracts pertinent data from the query, converts the extracted data to SQL, then retrieves the data from the database. AlLaDIn is domain-dependent, database-dependent natural language interface for CBMS-Pasay. 2. System Architecture AlLaDIn is concerned with translating the English query by the user into its corresponding SQL query to retrieve the data from the database. The result will then be displayed to the user. This system has four major modules, as shown in the architectural design of the system in Figure 1. This design is partially based on the Masque/SQL system (Androutsopoulos et al., 1995) and the FST mapping technique (Gala, 2005). 2.1 Parser and Semantic Analyzer This phase involves the (1) the tokenization of input, (2) parsing and analyzing the semantics of * Copyright 2008 by Krissanne Kaye Garcia, Ma. Angelica Lumain, Jose Antonio Wong, Jhovee Gerard Yap, Charibeth Cheng 384 22nd Pacific Asia Conference on Language, Information and Computation, pages 384–390 words, (3) retrieval of syntactic and semantic properties …

Content truncated to 500 words