KeEL: knowledge enhanced entity linking in automatic biography construction
Biography is a direct and extensive way to know the representation of well known peoples, however, for common people, there is poor knowledge for them to be recognized. In recent years, information extraction (IE) technologies have been used to automatically generate biography for any people with on...
Saved in:
Published in | Journal of China universities of posts and telecommunications Vol. 22; no. 1; pp. 57 - 64 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Elsevier Ltd
01.02.2015
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Biography is a direct and extensive way to know the representation of well known peoples, however, for common people, there is poor knowledge for them to be recognized. In recent years, information extraction (IE) technologies have been used to automatically generate biography for any people with online information. One of the key challenges is the entity linking (EL) which can link biography sentence to corresponding entities. Currently the used general EL systems usually generate errors originated from entity name variation and ambiguity. Compared with general text, biography sentences possess unique yet rarely studied relational knowledge (RK) and temporal knowledge (TK), which could sufficiently distinguish entities. This article proposed a new statistical framework called the knowledge enhanced EL (KeEL) system for automated biography construction. It utilizes commonsense knowledge like PK and TK to enhance Entity Linking. The performance of KeEL on Wikipedia data was evaluated. It is shown that, compared with state-of-the-art method, KeEL significantly improves the precision and recall of Entity Linking. |
---|---|
Bibliography: | knowledge enhanced entity linking, entity linking, biography construction, Markov logic network, Knowledge 11-3486/TN Biography is a direct and extensive way to know the representation of well known peoples, however, for common people, there is poor knowledge for them to be recognized. In recent years, information extraction (IE) technologies have been used to automatically generate biography for any people with online information. One of the key challenges is the entity linking (EL) which can link biography sentence to corresponding entities. Currently the used general EL systems usually generate errors originated from entity name variation and ambiguity. Compared with general text, biography sentences possess unique yet rarely studied relational knowledge (RK) and temporal knowledge (TK), which could sufficiently distinguish entities. This article proposed a new statistical framework called the knowledge enhanced EL (KeEL) system for automated biography construction. It utilizes commonsense knowledge like PK and TK to enhance Entity Linking. The performance of KeEL on Wikipedia data was evaluated. It is shown that, compared with state-of-the-art method, KeEL significantly improves the precision and recall of Entity Linking. Zhang Tianlei , Zhang Xinyu, Guo Mu (Computer Science Department, Tsinghua University, Beijing 100084, China) ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ISSN: | 1005-8885 |
DOI: | 10.1016/S1005-8885(15)60625-2 |