Proceedings of the 2007 ACM Symposium on Applied Computing 2007
DOI: 10.1145/1244002.1244188
|View full text |Cite
|
Sign up to set email alerts
|

Using a knowledge base to disambiguate personal name in web search results

Abstract: Results of queries by personal names often contain documents related to several people because of the namesake problem. In order to differentiate documents related to different people, an effective method is needed to measure document similarities and to find documents related to the same person. Some previous researchers have used the vector space model or have tried to extract common named entities for measuring similarities. We propose a new method that uses Web directories as a knowledge base to find share… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
10
0

Year Published

2007
2007
2012
2012

Publication Types

Select...
3
2
2

Relationship

2
5

Authors

Journals

citations
Cited by 14 publications
(10 citation statements)
references
References 6 publications
0
10
0
Order By: Relevance
“…The first method is based on a hierarchical clustering strategy and the second one makes use of social networks. Vu et al (2007) propose the use of Web directories as a knowledge base to disambiguate personal names in Web search results, whereas Bekkerman and McCallum (2005) present two methods for addressing this same problem, one based on the link structure of the Web pages and the other one using agglomerative/conglomerative double clustering, a multi‐way distributional clustering. Galvez and de Moya‐Anegón (2007) address the problem of conflating personal name variants in a canonical form using binary matrices and finite‐state graphs.…”
Section: Related Workmentioning
confidence: 99%
“…The first method is based on a hierarchical clustering strategy and the second one makes use of social networks. Vu et al (2007) propose the use of Web directories as a knowledge base to disambiguate personal names in Web search results, whereas Bekkerman and McCallum (2005) present two methods for addressing this same problem, one based on the link structure of the Web pages and the other one using agglomerative/conglomerative double clustering, a multi‐way distributional clustering. Galvez and de Moya‐Anegón (2007) address the problem of conflating personal name variants in a canonical form using binary matrices and finite‐state graphs.…”
Section: Related Workmentioning
confidence: 99%
“…A great deal of research has focused on the name disambiguation problem in different types of data, such as geographic name disambiguation [6], biomedical term disambiguation [7], and personal name disambiguation [8]. Several papers [1,9,10,11] have also focused on using the content in citations to solve the name disambiguation problem.…”
Section: Related Workmentioning
confidence: 99%
“…In [9], we proposed a modification method for tf to improve measurement of terms' weight. Here, we present a brief summarization of that method.…”
Section: Modification Of Tfmentioning
confidence: 99%
“…Therefore, we try to evaluate all clusters whose sizes are larger than three. The details on calculation of evaluation metrics can be found in [9]. The evaluation results of four methods VSM, NER, SKB1 and SKB2 and comparison among them are shown in Table 3.…”
Section: Evaluation Of Large Clustersmentioning
confidence: 99%