Templates of generic geographic information for answering where-questions

TL;DR

This paper introduces templates derived from a large dataset to automatically generate relevant geographic descriptions for answering where-questions, mimicking human responses by selecting key anchor places.

Contribution

It presents a novel approach using generic geographic information templates and sequence prediction to automate the generation of place descriptions for where-questions.

Findings

Templates effectively characterize human-generated answers.

Sequence prediction models can predict relevant answer templates.

Approach improves automatic answering of geographic where-questions.

Abstract

In everyday communication, where-questions are answered by place descriptions. To answer where-questions automatically, computers should be able to generate relevant place descriptions that satisfy inquirers' information needs. Human-generated answers to where-questions constructed based on a few anchor places that characterize the location of inquired places. The challenge for automatically generating such relevant responses stems from selecting relevant anchor places. In this paper, we present templates that allow to characterize the human-generated answers and to imitate their structure. These templates are patterns of generic geographic information derived and encoded from the largest available machine comprehension dataset, MS MARCO v2.1. In our approach, the toponyms in the questions and answers of the dataset are encoded into sequences of generic information. Next, sequence prediction methods are used to model the relation between the generic information in the questions and their answers. Finally, we evaluate the performance of predicting templates for answers to where-questions.