An extracted database content from WordNet for Natural Language Processing and Word Games

Abstract

WordNet which is available online and in desktop applications, is an English dictionary where the synonym sets of group of words are linked by means of semantic relations such as hyponymy, meronymy and entailment, among others. The main objective of this paper is to provide the Natural Language Processing (NLP) researchers and Word Game developers with a database such that WordNet content are accessed using simple Structured Query Language (SQL) queries. A distribution copy of Wordnet 3.0 database was downloaded, and loaded into a mySQL database. It was then migrated to Oracle where the database processing to accomplish the objectives of this project was performed. There were 7 tables, 32 materialized views and 4 stored functions constructed. It is at the WordNet dictionary displays that an NLP researcher will initially investigate what Wordnet content he/she needs. Most of the objects were created with reference to the displays. The aim was to come-up with simple SQLs such that the output of an SQL is similar to what is displayed online. Queries to extract content for some Word Games such as HangarooTM and Batang Henyo™ (Genius Child) exemplified the use of this project for Word Games. For Oracle users, distribution copies were made available in a collection of SQL scripts. Non-Oracle users were provided with Excel spreadsheets, Comma Separated Values (CSV) and eXtended Markup Language (XML) files that they can import or load.