arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.14909cs.CLcs.AIcs.LG
收藏

将表面事实链接到大规模知识图谱

Linking Surface Facts to Large-Scale Knowledge Graphs

NEC Laboratories Europe(NEC欧洲实验室);KU Leuven(荷语鲁汶大学);Ss. Cyril and Methodius University(圣西里尔与美多德大学);University of Würzburg(维尔茨堡大学)

Gorjan Radevski, Kiril Gashteovski, Chia-Chien Hung, Carolin Lawrence, Goran Glavaš

AI总结:

针对开放信息抽取表面事实的歧义性与知识图谱覆盖受限的问题,提出细粒度事实链接新基准及评估协议,发现KG外实体和谓词检测更难,并公开相关资源。

摘要:

开放信息抽取(Open Information Extraction, OIE)方法以(“主语”;“关系”;“宾语”)三元组的形式从自然语言文本中提取事实。然而,这些事实仅仅是表面形式,其歧义性阻碍了它们的下游使用;例如,表面短语“Michael Jordan”可能指代前篮球运动员,也可能指代大学教授。另一方面,知识图谱(Knowledge Graphs, KGs)以规范化(即无歧义)的形式包含事实,但其覆盖范围受限于静态模式(即固定的实体和谓词集合)。为了弥合这一差距,我们需要两者的优势:(i)自由文本OIE的高覆盖率,以及(ii)KG的语义精确性(即单义性)。为了实现这一目标,我们提出了一个带有新颖评估协议的新基准,例如,该协议可以在细粒度的三元组槽位级别上衡量事实链接性能,同时衡量系统是否具备识别表面形式在现有KG中没有匹配项的能力。我们对几个基线的广泛评估表明,检测KG外实体和谓词比准确链接到现有实体和谓词更困难,因此需要在这个困难的任务上投入更多研究努力。我们在 https://github.com/nec-research/fact-linking 上公开发布所有资源(数据、基准和代码)。

英文摘要:

Open Information Extraction (OIE) methods extract facts from natural language text in the form of ("subject"; "relation"; "object") triples. These facts are, however, merely surface forms, the ambiguity of which impedes their downstream usage; e.g., the surface phrase "Michael Jordan" may refer to either the former basketball player or the university professor. Knowledge Graphs (KGs), on the other hand, contain facts in a canonical (i.e., unambiguous) form, but their coverage is limited by a static schema (i.e., a fixed set of entities and predicates). To bridge this gap, we need the best of both worlds: (i) high coverage of free-text OIEs, and (ii) semantic precision (i.e., monosemy) of KGs. In order to achieve this goal, we propose a new benchmark with novel evaluation protocols that can, for example, measure fact linking performance on a granular triple slot level, while also measuring if a system has the ability to recognize that a surface form has no match in the existing KG. Our extensive evaluation of several baselines show that detection of out-of-KG entities and predicates is more difficult than accurate linking to existing ones, thus calling for more research efforts on this difficult task. We publicly release all resources (data, benchmark and code) on https://github.com/nec-research/fact-linking.

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。

↑