KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917886313889792 |
|---|---|
| author | Zhou, Zelin Conia, Simone Lee, Daniel Li, Min Huang, Shenglei Minhas, Umar Farooq Potdar, Saloni Xiao, Henry Li, Yunyao |
| author_facet | Zhou, Zelin Conia, Simone Lee, Daniel Li, Min Huang, Shenglei Minhas, Umar Farooq Potdar, Saloni Xiao, Henry Li, Yunyao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_03560 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphs Zhou, Zelin Conia, Simone Lee, Daniel Li, Min Huang, Shenglei Minhas, Umar Farooq Potdar, Saloni Xiao, Henry Li, Yunyao Computation and Language Artificial Intelligence Machine Learning 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. |
| title | KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphs |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2501.03560 |