Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs

TL;DR

This paper introduces the task of enhancing multilingual knowledge graphs by increasing the coverage and quality of non-English textual data, proposing a new unsupervised method and a benchmark to evaluate progress.

Contribution

It presents M-NTA, a novel unsupervised approach combining MT, Web Search, and LLMs, and introduces WikiKGE-10, a benchmark for multilingual knowledge graph evaluation.

Findings

State-of-the-art methods struggle with multilingual coverage.

M-NTA improves the quality of non-English textual information.

Enhanced multilingual data benefits entity linking, KG completion, and QA.

Abstract

Recent work in Natural Language Processing and Computer Vision has been using textual information -- e.g., entity names and descriptions -- available in knowledge graphs to ground neural models to high-quality structured data. However, when it comes to non-English languages, the quantity and quality of textual information are comparatively scarce. To address this issue, we introduce the novel task of automatic Knowledge Graph Enhancement (KGE) and perform a thorough investigation on bridging the gap in both the quantity and quality of textual information between English and non-English languages. More specifically, we: i) bring to light the problem of increasing multilingual coverage and precision of entity names and descriptions in Wikidata; ii) demonstrate that state-of-the-art methods, namely, Machine Translation (MT), Web Search (WS), and Large Language Models (LLMs), struggle with this task; iii) present M-NTA, a novel unsupervised approach that combines MT, WS, and LLMs to generate high-quality textual information; and, iv) study the impact of increasing multilingual coverage and precision of non-English textual information in Entity Linking, Knowledge Graph Completion, and Question Answering. As part of our effort towards better multilingual knowledge graphs, we also introduce WikiKGE-10, the first human-curated benchmark to evaluate KGE approaches in 10 languages across 7 language families.