arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.14733cs.AIcs.CLcs.LG
收藏

基于多任务学习的开放知识库规范化

Open Knowledge Base Canonicalization with Multi-task Learning

School of Software, Shandong University(山东大学软件学院);Laboratory for Big Data and Decision, National University of Defense Technology(国防科技大学大数据与决策实验室);QuanCheng Laboratory(泉城实验室)

Bingchen Liu, Huang Peng, Weixin Zeng, Xiang Zhao, Shijun Liu, Li Pan

AI总结:

针对开放知识库规范化中聚类与知识图谱嵌入学习协同不足的问题,提出多任务学习框架MulCanon,利用扩散模型改进名词短语表示并统一子任务学习目标,取得有竞争力的规范化结果。

摘要:

大型开放知识库(OKBs)的构建对于万维网上的许多知识驱动应用(如网络搜索)至关重要。然而,OKBs中的名词短语和关系短语常常存在冗余和歧义,这促使了对OKB规范化的研究。当前的解决方案通过设计先进的聚类算法并使用知识图谱嵌入(KGE)来进一步促进规范化过程来解决OKB规范化问题。然而,这些工作未能充分利用聚类与KGE学习之间的协同作用,且为这些子任务设计的方法是次优的。为此,我们提出了一个多任务学习框架,即MulCanon,来解决OKB规范化问题。此外,在软聚类过程中使用了扩散模型,利用邻域信息改进名词短语的表示,从而获得更准确的表示。MulCanon统一了这些子任务的学习目标,并采用两阶段多任务学习范式进行训练。在流行的OKB规范化基准上的全面实验研究验证了MulCanon能够取得有竞争力的规范化结果。

英文摘要:

The construction of large open knowledge bases (OKBs) is integral to many knowledge-driven applications on the world wide web such as web search. However, noun phrases and relational phrases in OKBs often suffer from redundancy and ambiguity, which calls for the investigation on OKB canonicalization. Current solutions address OKB canonicalization by devising advanced clustering algorithms and using knowledge graph embedding (KGE) to further facilitate the canonicalization process. Nevertheless, these works fail to fully exploit the synergy between clustering and KGE learning, and the methods designed for these subtasks are sub-optimal. To this end, we put forward a multi-task learning framework, namely MulCanon, to tackle OKB canonicalization. In addition, diffusion model is used in the soft clustering process to improve the noun phrase representations with neighboring information, which can lead to more accurate representations. MulCanon unifies the learning objectives of these sub-tasks, and adopts a two-stage multi-task learning paradigm for training. A thorough experimental study on popular OKB canonicalization benchmarks validates that MulCanon can achieve competitive canonicalization results.

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。

↑