KG-TRICK：统一多语言知识图谱的文本与关系信息补全
KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphs
AI总结：
本文提出 KG-TRICK 序列到序列框架，将多语言知识图谱的关系补全 KGC 与文本增强 KGE 统一建模，并发布涵盖10种语言、逾25,000个实体的 WikiKGE10++ 基准。
摘要：
多语言知识图谱（KG）为各类 NLP 应用提供高质量的关系和文本信息，但它们往往并不完整，在非英语语言中尤其如此。此前研究表明，结合来自不同语言 KG 的信息，有助于知识图谱补全（KGC，即预测实体之间缺失关系的任务）或知识图谱增强（KGE，即为实体预测缺失文本信息的任务）。尽管以往工作将 KGC 和 KGE 视为相互独立的任务，但我们假设二者相互依赖且互惠互利。为此，我们提出 KG-TRICK，这是一种新颖的序列到序列框架，统一了面向多语言 KG 的文本信息补全与关系信息补全任务。KG-TRICK 表明：i）将 KGC 和 KGE 任务统一到单一框架中是可行的；ii）结合多种语言的文本信息有助于提升 KG 的完整性。作为贡献的一部分，我们还提出 WikiKGE10++，这是用于 KG 文本信息补全的最大人工整理基准，涵盖10种不同语言中的25,000多个实体。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
