A Method for Multi-Hop Question Answering on Persian Knowledge Graph

TL;DR

This paper introduces a new method for multi-hop question answering in Persian knowledge graphs, involving dataset creation, language model training, and an architecture that improves answer accuracy and F1-score.

Contribution

The study develops a Persian multi-hop question dataset, trains language models, and proposes an architecture that enhances question understanding and answer retrieval in Persian KGQA.

Findings

12.57% improvement in F1-score

12.06% increase in accuracy

Superior performance on PeCoQ dataset

Abstract

Question answering systems are the latest evolution in information retrieval technology, designed to accept complex queries in natural language and provide accurate answers using both unstructured and structured knowledge sources. Knowledge Graph Question Answering (KGQA) systems fulfill users' information needs by utilizing structured data, representing a vast number of facts as a graph. However, despite significant advancements, major challenges persist in answering multi-hop complex questions, particularly in Persian. One of the main challenges is the accurate understanding and transformation of these multi-hop complex questions into semantically equivalent SPARQL queries, which allows for precise answer retrieval from knowledge graphs. In this study, to address this issue, a dataset of 5,600 Persian multi-hop complex questions was developed, along with their decomposed forms based on the semantic representation of the questions. Following this, Persian language models were trained using this dataset, and an architecture was proposed for answering complex questions using a Persian knowledge graph. Finally, the proposed method was evaluated against similar systems on the PeCoQ dataset. The results demonstrated the superiority of our approach, with an improvement of 12.57% in F1-score and 12.06% in accuracy compared to the best comparable method.