Multilingual Knowledge Graph Completion with Joint Relation and Entity Alignment

Abstract

Knowledge Graph Completion (KGC) predicts missing facts in an incomplete Knowledge Graph. Almost all of existing KGC research is applicable to only one KG at a time, and in one language only. However, different language speakers may maintain separate KGs in their language and no individual KG is expected to be complete. Moreover, common entities or relations in these KGs have different surface forms and IDs, leading to ID proliferation. Entity alignment (EA) and relation alignment (RA) tasks resolve this by recognizing pairs of entity (relation) IDs in different KGs that represent the same entity (relation). This can further help prediction of missing facts, since knowledge from one KG is likely to benefit completion of another. High confidence predictions may also add valuable information for the alignment tasks.In response, we study the novel task of jointly training multilingual KGC, relation alignment and entity alignment models. We present ALIGNKGC, which uses some seed alignments to jointly optimize all three of KGC, EA and RA losses. A key component of ALIGN-KGC is an embedding-based soft notion of asymmetric overlap defined on the (subject, object) set signatures of relations -this aids in better predicting relations that are equivalent to or implied by other relations. Extensive experiments with DBPedia in five languages establish the benefits of joint training for all tasks, achieving 10-32 MRR improvements of ALIGNKGC over a strong state-ofthe-art single-KGC system completion model over each monolingual KG . Further, ALIGN-KGC achieves reasonable gains in EA and RA tasks over a vanilla completion model over a KG that combines all facts without alignment, underscoring the value of joint training for these tasks.

A Comparative Study of ChatGPT-based and Hybrid Parser-based Sentence Parsing Methods for Semantic Graph-based Induction

“…Recently, word embeddings and entity embeddings have become effective in capturing semantic relationships, and the advancements in embedding techniques continue to improve graph construction [3]. Ensuring the completeness and accuracy of knowledge graphs is an ongoing challenge [4], [5], with methods for knowledge base completion and alignment being actively explored [6].…”

Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment

“…vlin et al, 2019) to obtain initial embeddings of entities and relations from their text for all methods. We do not employ any pretrained tasks such as EA to obtain these initial text embeddings as in (Singh et al, 2021).…”

“…Multilingual KG embeddings are extensions of monolingual KG embeddings that consider knowledge transfer across KGs with the use of limited seed alignment Singh et al, 2021). Earlier work proposes different ways to reconcile KG embeddings for the entity alignment (EA) task: MTransE (Chen et al, 2017) learns a transformation matrix between pairs of KGs.…”

“…We revise its loss function to conduct MKGC. (iii) AlignKGC(Singh et al, 2021) jointly trains the KGC loss with entity and relation alignment losses. For fair comparison, we use mBERT (De…”