Boolean Retrieval Model

Boolean retrieval

Boolean retrieval also known as "exact match" model is based on Boolean logic in that both the documents to be searched and the user's query are conceived as sets of terms. The Retrieval is based on whether or not the documents contain the query terms (Boolean retrieval, n.d.)

Boolean retrieval has the following strengths:

1) It is easy to implement and it is computationally efficient according to Frakes and Baeza-Yates (1992). Hence, it is the standard model for the current large-scale, operational retrieval systems and many of the major on-line information services use it (Information Retrieval Models, n.d.).

2 Frakes and Baeza-Yates (1992) further states that it enables users to express structural and conceptual constraints

Some of Boolean model disadvantages include the fact that Users find it difficult to construct effective Boolean queries for several reasons such as when Users are using the natural language terms AND, OR or NOT that have a different meaning when used in a query which can cause them to make errors when they form a Boolean query based on their real linguistic meaning (Croft, 1986).

Different methods can be used to improve scoring and ranking in search systems. These methods can include both safe where only the exact match of the search query should appear in the search results and un-safe ranking where a percentage of wrong or unrelated search results can appear as part of the search results. Some these techniques include index elimination where for a multi-term query q, the only consideration is for documents containing at least one of the query terms. This could entail only considering documents containing terms whose idf exceeds a pre-set threshold. Secondly, creating Champion lists where for each term t in the dictionary, the set of the r documents with the highest weights for t and the value of r is chosen in advance. The Champion list will consists of the r documents with the highest tf values for term t. thirdly, cluster pruning we have a pre-processing phase during which we cluster

In phrase query consecutive terms are treated as bi-words.

References

Boolean retrieval. (n.d.). Retrieved October 10, 2017, from Stanford: https://nlp.stanford.edu/IR-book/html/htmledition/boolean-retrieval-1.html

Croft, B. W. (1986). Boolean queries and term dependencies in probabilistic retrieval models. J. Am. Soc. Inf. Sci, 2, 37.

Frakes, W. B., & Baeza-Yates, R. (1992). Information retrieval: data structures and algorithms. Upper Saddle , NJ, US: Prentice-Hall, Inc.

Information Retrieval Models. (n.d.). Retrieved October 10, 2017, from Anselm Spoerri: http://aspoerri.comminfo.rutgers.edu/InfoCrystal/Ch_2.html

Wildcard queries. (n.d.). Retrieved October 10, 2017, from Stanford: https://nlp.stanford.edu/IR-book/html/htmledition/wildcard-queries-1.html#3677

Manning, C.D., Raghaven, P., & Schütze, H. (2009). An Introduction to Information Retrieval. Retrieved from