蘸取PLMs酱汁:通过条件软提示桥接结构与文本以实现高效知识图谱补全
Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting
AI总结:
本文提出CSProm-KG方法,通过条件软提示在知识图谱补全中平衡结构信息与文本知识,在多个静态和时序基准上取得最优结果。
摘要:
知识图谱补全(KGC)通常需要同时利用知识图谱的结构信息和文本信息才能取得良好效果。预训练语言模型(PLMs)已被用于学习文本信息,通常在KGC任务中采用微调范式。然而,微调后的PLMs往往过度关注文本信息而忽视结构知识。为解决这一问题,本文提出CSProm-KG(用于KGC的条件软提示),它在结构信息和文本知识之间保持平衡。CSProm-KG仅调优由实体和关系表示生成的条件软提示的参数。我们在三个流行的静态KGC基准WN18RR、FB15K-237和Wikidata5M,以及两个时序KGC基准ICEWS14和ICEWS05-15上验证了CSProm-KG的有效性。CSProm-KG优于竞争性基线模型,并在这些基准上取得了新的最优结果。我们进行了进一步分析,展示了(i)所提出各组件的有效性,(ii)CSProm-KG的效率,以及(iii)CSProm-KG的灵活性。
英文摘要:
Knowledge Graph Completion (KGC) often requires both KG structural and textual information to be effective. Pre-trained Language Models (PLMs) have been used to learn the textual information, usually under the fine-tune paradigm for the KGC task. However, the fine-tuned PLMs often overwhelmingly focus on the textual information and overlook structural knowledge. To tackle this issue, this paper proposes CSProm-KG (Conditional Soft Prompts for KGC) which maintains a balance between structural information and textual knowledge. CSProm-KG only tunes the parameters of Conditional Soft Prompts that are generated by the entities and relations representations. We verify the effectiveness of CSProm-KG on three popular static KGC benchmarks WN18RR, FB15K-237 and Wikidata5M, and two temporal KGC benchmarks ICEWS14 and ICEWS05-15. CSProm-KG outperforms competitive baseline models and sets new state-of-the-art on these benchmarks. We conduct further analysis to show (i) the effectiveness of our proposed components, (ii) the efficiency of CSProm-KG, and (iii) the flexibility of CSProm-KG.
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。