Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Song, Ran, He, Shizhu, Gao, Shengxiang, Cai, Li, Liu, Kang, Yu, Zhengtao, Zhao, Jun
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917705645293568
author Song, Ran
He, Shizhu
Gao, Shengxiang
Cai, Li
Liu, Kang
Yu, Zhengtao
Zhao, Jun
author_facet Song, Ran
He, Shizhu
Gao, Shengxiang
Cai, Li
Liu, Kang
Yu, Zhengtao
Zhao, Jun
contents Multilingual Knowledge Graph Completion (mKGC) aim at solving queries like (h, r, ?) in different languages by reasoning a tail entity t thus improving multilingual knowledge graphs. Previous studies leverage multilingual pretrained language models (PLMs) and the generative paradigm to achieve mKGC. Although multilingual pretrained language models contain extensive knowledge of different languages, its pretraining tasks cannot be directly aligned with the mKGC tasks. Moreover, the majority of KGs and PLMs currently available exhibit a pronounced English-centric bias. This makes it difficult for mKGC to achieve good results, particularly in the context of low-resource languages. To overcome previous problems, this paper introduces global and local knowledge constraints for mKGC. The former is used to constrain the reasoning of answer entities, while the latter is used to enhance the representation of query contexts. The proposed method makes the pretrained model better adapt to the mKGC task. Experimental results on public datasets demonstrate that our method outperforms the previous SOTA on Hits@1 and Hits@10 by an average of 12.32% and 16.03%, which indicates that our proposed method has significant enhancement on mKGC.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18085
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints
Song, Ran
He, Shizhu
Gao, Shengxiang
Cai, Li
Liu, Kang
Yu, Zhengtao
Zhao, Jun
Computation and Language
Multilingual Knowledge Graph Completion (mKGC) aim at solving queries like (h, r, ?) in different languages by reasoning a tail entity t thus improving multilingual knowledge graphs. Previous studies leverage multilingual pretrained language models (PLMs) and the generative paradigm to achieve mKGC. Although multilingual pretrained language models contain extensive knowledge of different languages, its pretraining tasks cannot be directly aligned with the mKGC tasks. Moreover, the majority of KGs and PLMs currently available exhibit a pronounced English-centric bias. This makes it difficult for mKGC to achieve good results, particularly in the context of low-resource languages. To overcome previous problems, this paper introduces global and local knowledge constraints for mKGC. The former is used to constrain the reasoning of answer entities, while the latter is used to enhance the representation of query contexts. The proposed method makes the pretrained model better adapt to the mKGC task. Experimental results on public datasets demonstrate that our method outperforms the previous SOTA on Hits@1 and Hits@10 by an average of 12.32% and 16.03%, which indicates that our proposed method has significant enhancement on mKGC.
title Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints
topic Computation and Language
url https://arxiv.org/abs/2406.18085