Answer Ranking with Weighted Scores in Indonesian Hybrid Restricted Domain Question Answering System

摘要

The increased availability of information on the WWW has made it more challenging to select and filter information that we require. As a result, there is a greater demand for question-answering systems. Question Answering System responds to natural language-based questions from the user. However, traditionally, ranking the answers is based on the availability of the user's query terms in the candidate documents, which results in lower performance. The goal of this paper is to address the problem of ranking answer candidates for factoid-based questions. We improved the Answer Extraction by adding weight and several features and tokens of questions to determine the candidate's answer. We also enhanced the Question Analysis phase by joining phrase queries and boolean combination queries. Based on the results of our experiments, our proposed framework had the best performance of 54%.