ditlab system for Dialogue Robot Competition 2022

TL;DR

This paper presents a dialogue system designed for the 2022 Dialogue Robot Competition, integrating demographic analysis, POI recommendation, and hybrid question answering methods.

Contribution

It introduces a multi-component dialogue system combining rule-based and deep learning techniques for competition purposes.

Findings

Effective demographic data collection via rule-based interview

Accurate POI recommendations based on demographic info

Hybrid question answering improves response relevance

Abstract

We developed a dialogue system for Dialogue Robot Competition 2022. Our system is composed of three parts. First part investigates participants' demographic information by rule-based interview. Second part recommends a point of interest (POI) based on the collected demographic information. Third part answers participants' question based on the combination of rule-based answering and deep-learning-based answering with nearby POI search.