Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs
This work addresses the problem of limited multilingual textual data in knowledge graphs for researchers and practitioners in NLP, though it is incremental as it builds on existing methods like MT and LLMs.
The paper tackles the scarcity of high-quality textual information in non-English knowledge graphs by introducing the task of automatic Knowledge Graph Enhancement (KGE) and proposing M-NTA, an unsupervised method that combines machine translation, web search, and large language models to generate such information. It shows that M-NTA improves entity linking, knowledge graph completion, and question answering, with results including the creation of WikiKGE-10, a benchmark for 10 languages.
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.