A Method of Passage-Based Document Retrieval in Question Answering System

TL;DR

This paper introduces a passage-based document retrieval method for question answering systems that uses a proximity-aware scoring function to select the most relevant documents, demonstrating effectiveness in Korean QA systems.

Contribution

It presents a novel evaluation function considering term proximity for improved document retrieval in question answering systems.

Findings

Effective retrieval of relevant documents in Korean QA systems

Proximity-based scoring improves document relevance

Method outperforms previous retrieval approaches

Abstract

We propose a method for using the scoring values of passages to effectively retrieve documents in a Question Answering system. For this, we suggest evaluation function that considers proximity between each question terms in passage. And using this evaluation function , we extract a documents which involves scoring values in the highest collection, as a suitable document for question. The proposed method is very effective in document retrieval of Korean question answering system.