A hybrid approach to fuzzy name search incorporating language-based and text-based principles

Abstract

Name Search is an important search function in various types of information retrieval systems, such as online library catalogs and electronic yellow pages. It is also difficult due to the high degree of fuzziness required in matching name variants. Previous approaches to name search systems use ad hoc combinations of search heuristics. This paper first discusses two approaches to name modeling-the natural language processing (NLP) and the information retrieval (IR) models-and proposes a hybrid approach. The approach demonstrates a critical combination of complementary NLP and IR features that produces more effective fuzzy name matching. Two principles, position-as-attribute and position-transitionlikelihood, are introduced as the principles for integrating the advantageous aspects of both approaches. They have been implemented in an NLP-and IR-hybrid model system called Friendly Name Search (FNS) for real world applications in multilingual directory searches on the Singapore Yellow pages website.

Mapping Letters through Interaction Design

“…This will require that we take real-time processing and new interaction functionalities into account when further developing the GertrudeMapper tool. For example, a future development of the particle visualiser might contemplate elaborating an automated text transcription, or implementing algorithms that would perform Fuzzy Searches or approximate string matching (the technique of finding approximate matches to a pattern in a string) (Horng-Jyh et al, 2007).…”

Affective mapping of social networks

“…This will require further developments of the GertrudeMapper tool. For example, a future development of the tool might contemplate the elaboration of an automatic transcription of texts, or the implementation of algorithms in order to perform Fuzzy Search or approximate string matching, which is the technique of finding approximate matches to a pattern in a string [13].…”

A cascaded approach for Chinese clinical text de-identification with less annotation effort

“…For names alone, there are currently over 4,000 Chinese surnames in use and 106,000 individual Chinese characters for given names. It is also difficult to identify names because of the high degree of fuzziness required in matching the first name and the second name [23]. Joint with the challenge of word segmentation, a Chinese name can be very challenging to be distinguished from a sequence of Chinese characters.…”