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 ALIGNKGC 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-of-the-art single-KGC system completion model over each monolingual KG . Further, ALIGNKGC 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.
翻译:知识图补全( KGC) 预测了一个不完整的知识图中缺少的事实。 几乎所有现有的 KGC 研究都只适用于一个 KG, 并且只使用一种语言。 但是, 不同的语言语言的使用者可以使用自己的语言保持不同的 KG, 而没有单个的 KG 能够完成。 此外, 这些 KG 的共同实体或关系有不同的表面格式和ID, 导致ID扩散。 实体对齐( EA) 和关系对齐( RA) 的任务通过承认代表同一实体( 关系) 的不同 KG 的实体对齐( 关系) 来解决这个问题。 这可以进一步帮助预测缺失的事实, 因为来自一个 KG 的知识可能有利于完成另一种语言的知识。 高信任预测也可能为校准任务增加有价值的信息。 作为回应,我们研究联合培训多语言KGC、 关系对关系校正和实体对模型的匹配( EAIG ) 任务, 使用某些种子对齐来联合优化所有三种KGC、 EA 和RA 损失。 ALIK 的关键部分是建立在一个基于对等的软概念的软概念上, 。 KG ( 主题、 目标目标) 将所有OLILG 联合对等的升级任务, 建立联盟关系中, 建立联盟关系中, 联盟对等的连结结结为D, 建立更好的对等关系, 建立联盟关系, 建立联盟关系, 建立联盟关系, 建立联盟关系, 建立联盟关系, 建立联盟关系, 建立联盟关系, 建立联盟关系, 联盟对等关系, 建立联盟关系, 建立联盟关系, 建立联盟关系, 建立联盟关系, 建立联盟关系, 联盟关系, 建立联盟对等关系, 建立联盟关系, 联盟对等关系, 联盟对等关系, 建立联盟关系, 联盟关系, 联盟关系, 联盟联盟关系, 联盟联盟关系, 联盟关系, 联盟联盟联盟联盟联盟联盟联盟联盟联盟联盟联盟联盟联盟联盟联盟联盟联盟联盟联盟关系, 联盟联盟关系, 联盟关系 联盟关系 联盟关系 联盟关系 联盟联盟联盟的契约关系 联盟 联盟关系 联盟 建立联盟关系 联盟关系 联盟关系 联盟关系 联盟关系 联盟关系 联盟关系,