Extracting Key Phrases to Disambiguate Personal Names on the Web

Abstract. When you search for information regarding a particular person on the web, a search engine returns many pages. Some of these pages may be for people with the same name. How can we disambiguate these different people with the same name? This paper presents an unsupervised algorithm which produces key phrases for the different people with the same name. These key phrases could be used to further narrow down the search, leading to more person specific unambiguous information. The algorithm we propose does not require any biographical or social information regarding the person. Although there are some previous work in personal name disambiguation on the web, to our knowledge, this is the first attempt to extract key phrases to disambiguate the different persons with the same name. To evaluate our algorithm, we collected and hand labeled a dataset of over 1000 Web pages retrieved from Google using personal name queries. Our experimental results shows an improvement over the existin...

• Type: Conference
• Year: 2006
• Where: CICLING
• Authors: Danushka Bollegala, Yutaka Matsuo, Mitsuru Ishizuka
• Keywords: CICLING 2006, Key Phrases, Natural Language Processing, Particular Person, Personal Name Disambiguation