A Knowledge-based Approach for Answering Complex Questions in Persian

TL;DR

This paper presents a knowledge-based method for answering complex questions in Persian by leveraging a Persian knowledge graph and a new dataset, improving accuracy in low-resource language QA.

Contribution

It introduces a novel approach combining logical form generation and Multilingual-BERT for Persian complex question answering, along with a new dataset PeCoQ.

Findings

Outperforms existing methods in Persian CQA

Effective handling of multi-constraint and multi-hop questions

Demonstrates the viability of knowledge-based QA in low-resource languages

Abstract

Research on open-domain question answering (QA) has a long tradition. A challenge in this domain is answering complex questions (CQA) that require complex inference methods and large amounts of knowledge. In low resource languages, such as Persian, there are not many datasets for open-domain complex questions and also the language processing toolkits are not very accurate. In this paper, we propose a knowledge-based approach for answering Persian complex questions using Farsbase; the Persian knowledge graph, exploiting PeCoQ; the newly created complex Persian question dataset. In this work, we handle multi-constraint and multi-hop questions by building their set of possible corresponding logical forms. Then Multilingual-BERT is used to select the logical form that best describes the input complex question syntactically and semantically. The answer to the question is built from the answer to the logical form, extracted from the knowledge graph. Experiments show that our approach outperforms other approaches in Persian CQA.