KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphs

TL;DR

KG-TRICK is a unified sequence-to-sequence framework that enhances multilingual knowledge graphs by jointly completing missing relations and textual information, leveraging multilingual data for improved KG completeness.

Contribution

It introduces KG-TRICK, the first unified model for both relation and textual completion in multilingual KGs, and presents WikiKGE10++, a large benchmark dataset.

Findings

Unified KGC and KGE tasks improve KG completeness.

Multilingual textual data enhances relation prediction.

KG-TRICK outperforms separate models on benchmark datasets.

Abstract

Multilingual knowledge graphs (KGs) provide high-quality relational and textual information for various NLP applications, but they are often incomplete, especially in non-English languages. Previous research has shown that combining information from KGs in different languages aids either Knowledge Graph Completion (KGC), the task of predicting missing relations between entities, or Knowledge Graph Enhancement (KGE), the task of predicting missing textual information for entities. Although previous efforts have considered KGC and KGE as independent tasks, we hypothesize that they are interdependent and mutually beneficial. To this end, we introduce KG-TRICK, a novel sequence-to-sequence framework that unifies the tasks of textual and relational information completion for multilingual KGs. KG-TRICK demonstrates that: i) it is possible to unify the tasks of KGC and KGE into a single framework, and ii) combining textual information from multiple languages is beneficial to improve the completeness of a KG. As part of our contributions, we also introduce WikiKGE10++, the largest manually-curated benchmark for textual information completion of KGs, which features over 25,000 entities across 10 diverse languages.