mRAKL: Multilingual Retrieval-Augmented Knowledge Graph Construction for Low-Resourced Languages

TL;DR

This paper introduces mRAKL, a retrieval-augmented system that reformulates multilingual knowledge graph construction as a question answering task, improving accuracy especially for low-resource languages like Tigrinya and Amharic.

Contribution

The paper presents a novel RAG-based approach for multilingual KGC, reformulating it as QA and demonstrating improved performance with cross-lingual transfer.

Findings

RAG approach outperforms no-context baseline

Ideal retrieval boosts accuracy by nearly 5-9 percentage points

Effective for low-resource languages Tigrinya and Amharic

Abstract

Knowledge Graphs represent real-world entities and the relationships between them. Multilingual Knowledge Graph Construction (mKGC) refers to the task of automatically constructing or predicting missing entities and links for knowledge graphs in a multilingual setting. In this work, we reformulate the mKGC task as a Question Answering (QA) task and introduce mRAKL: a Retrieval-Augmented Generation (RAG) based system to perform mKGC. We achieve this by using the head entity and linking relation in a question, and having our model predict the tail entity as an answer. Our experiments focus primarily on two low-resourced languages: Tigrinya and Amharic. We experiment with using higher-resourced languages Arabic and English for cross-lingual transfer. With a BM25 retriever, we find that the RAG-based approach improves performance over a no-context setting. Further, our ablation studies show that with an idealized retrieval system, mRAKL improves accuracy by 4.92 and 8.79 percentage points for Tigrinya and Amharic, respectively.