PDF] Named entity disambiguation by leveraging wikipedia semantic
Por um escritor misterioso
Last updated 02 junho 2024
A novel similarity measure is proposed to leverage Wikipedia semantic knowledge for disambiguation, which surpasses other knowledge bases by the coverage of concepts, rich semantic information and up-to-date content and has been tested on the standard WePS data sets. Name ambiguity problem has raised an urgent demand for efficient, high-quality named entity disambiguation methods. The key problem of named entity disambiguation is to measure the similarity between occurrences of names. The traditional methods measure the similarity using the bag of words (BOW) model. The BOW, however, ignores all the semantic relations such as social relatedness between named entities, associative relatedness between concepts, polysemy and synonymy between key terms. So the BOW cannot reflect the actual similarity. Some research has investigated social networks as background knowledge for disambiguation. Social networks, however, can only capture the social relatedness between named entities, and often suffer the limited coverage problem. To overcome the previous methods' deficiencies, this paper proposes to use Wikipedia as the background knowledge for disambiguation, which surpasses other knowledge bases by the coverage of concepts, rich semantic information and up-to-date content. By leveraging Wikipedia's semantic knowledge like social relatedness between named entities and associative relatedness between concepts, we can measure the similarity between occurrences of names more accurately. In particular, we construct a large-scale semantic network from Wikipedia, in order that the semantic knowledge can be used efficiently and effectively. Based on the constructed semantic network, a novel similarity measure is proposed to leverage Wikipedia semantic knowledge for disambiguation. The proposed method has been tested on the standard WePS data sets. Empirical results show that the disambiguation performance of our method gets 10.7% improvement over the traditional BOW based methods and 16.7% improvement over the traditional social network based methods.
PDF] Named entity disambiguation by leveraging wikipedia semantic
PDF) Named entity disambiguation by leveraging wikipedia semantic
Generation of training data for named entity recognition of
Leveraging Semantic Fingerprinting for Building Author Networks
PDF) Graph-Based Named Entity Linking with Wikipedia
SVM ensembles for named entity disambiguation
Joint Modeling of Local and Global Semantics for Contrastive
Leveraging Semantic Fingerprinting for Building Author Networks
PDF) Named Entity Disambiguation for Noisy Text
Recomendado para você
-
Halo: The Television Series/Season One, Halo Alpha02 junho 2024
-
Halo Universe, Halo Alpha02 junho 2024
-
Halo 5: Guardians - Wikipedia02 junho 2024
-
Pablo Schreiber - Wikipedia02 junho 2024
-
Halo: Uprising - Wikipedia02 junho 2024
-
Halo (DC Comics) - Wikipedia02 junho 2024
-
Earth - Planet - Halopedia, the Halo wiki02 junho 2024
-
Warrior Nun (TV series) - Wikiwand02 junho 2024
-
Halo 3 - PCGamingWiki PCGW - bugs, fixes, crashes, mods, guides and improvements for every PC game02 junho 2024
-
Master Chief, Heroes Wiki02 junho 2024
você pode gostar
-
Crash!, Board Game02 junho 2024
-
100% Free Chess02 junho 2024
-
Digimon Adventure 02: The Beginning Review: A Welcome Reunion02 junho 2024
-
What anime completely ruined its plot or characters after season 1? - Quora02 junho 2024
-
Fall Guys - Como ganhar novas skins e itens cosméticos - Critical Hits02 junho 2024
-
Soundtrack - Rotten Tomatoes02 junho 2024
-
GTA San Andreas Game: How To Enter Cheats in GTA? - On PC, PS2 and Xbox02 junho 2024
-
MacBook Pro Final Cut Pro X Final Cut Studio, final cut pro icon, electronics, media, video Editing png02 junho 2024
-
Error occurred when installing ssl certificate - aaPanel - Hosting control panel. One-click LAMP/LEMP.02 junho 2024
-
Gerenciamento de Inventário e Pedidos de Ecommerce para Marcas e02 junho 2024