2016
DOI: 10.1016/j.websem.2015.12.005
|View full text |Cite
|
Sign up to set email alerts
|

Contextualized ranking of entity types based on knowledge graphs

Abstract: A large fraction of online queries target entities. For this reason, Search Engine Result Pages (SERPs) increasingly contain information about the searched entities such as pictures, short summaries, related entities, and factual information. A key facet that is often displayed on the SERPs and that is instrumental for many applications is the entity type. However, an entity is usually not associated to a single generic type in the background knowledge graph but rather to a set of more specific types, which ma… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
31
0
1

Year Published

2018
2018
2021
2021

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 34 publications
(32 citation statements)
references
References 21 publications
0
31
0
1
Order By: Relevance
“…The data is taken and processed, to yield adequate knowledge. The main advantages in our representation model are no prior knowledge about the scenario is required and no data training [13] is done. As the data is fed into the system, it is processed and the graph is constructed.…”
Section: Discussionmentioning
confidence: 99%
“…The data is taken and processed, to yield adequate knowledge. The main advantages in our representation model are no prior knowledge about the scenario is required and no data training [13] is done. As the data is fed into the system, it is processed and the graph is constructed.…”
Section: Discussionmentioning
confidence: 99%
“…面向特定任务的 实体摘要, 如用于共指消解的实体摘要方法 C3D+P [5] , 用于实体链接场景的 COMB [4] 等, 其生成的 摘要特定于要辅助用户完成的下游任务. 上下文相关的实体摘要, 如以查询 [3] 或文档内容 [18] 为上下 文, 摘要内容的选取需要考虑与上下文的相关度. 而更多的实体摘要研究则关注于通用场景, 即根据 实体和知识图谱自身的内容和特性, 自动生成可广泛应用于多种领域和应用的实体摘要.…”
Section: 冗余性的影响unclassified
“…Much of the work into searching semantically has been done in the context of searching the web. [17][18][19] Some of these works, such as RQL by Karvounarakis et al, 20 require users to formulate queries using some formal language or form, which leads to very precise searching that is inappropriate for naïve or everyday users. Glover et al 21 and Lei et al 22 aimed for a completely user-transparent solution where the user needs only to write a simple query with possible tags, while others still 23,24 aimed for a hybrid approach in which the system may ask a user for clarification on the meaning of their query.…”
Section: Semantic Searchmentioning
confidence: 99%