Information Extraction in a Set of Knowledge Using a Fuzzy Logic Based Intelligent Agent

Abstract

Abstract.A method for Information Extraction (IE) in a set of knowledge is proposed in this paper in order to answer to user consultations using natural language. The system is based on a fuzzy logic engine, which takes advantage of its flexibility for managing sets of accumulated knowledge. These sets can be built in hierarchic levels by a tree structure. A method of consultation based on a fuzzy logic application provided with an interface that one may interact with in natural language is also proposed. The eventual aim of this system is the implementation of an intelligent agent to manage the information contained in an internet portal.

A Novel Term Weighting Scheme for a Fuzzy Logic Based Intelligent Web Agent

“…As we did in (Ropero et al, 2007) tests are based on the use of standard-questions as user consultations. The first goal of these tests is to check that the system makes a correct identification of standardquestions with an index of certainty higher than 0.7.…”

“…In previous investigations, we have proposed the use of a fuzzy logic based intelligent agent for Information Extraction (IE) (Ropero et al, 2007). This proposal came from the need of approaching to the contents of an extensive set of accumulated knowledge and it is based on the fact that a set of objects may be qualified on closely related families.…”

“…Besides, due to the fact that IE system uses two fuzzy engines which do not work in the same way as it depends on the number of keywords, (Ropero, 2007) the proposed weight suffers a later modification depending on the number of keywords that represent the object. For the comparative study of the automatically obtained weight values and the ones that were proposed intuitively by the Knowledge Engineer, a specific application has been developed.…”

A Fuzzy Logic intelligent agent for Information Extraction: Introducing a new Fuzzy Logic-based term weighting scheme

“…The whole process, together with other concepts defined below, is shown in Fig. 5 364 (Ropero et al, 2007 Provided that the aim of the system is to find the possible an-367 swers to user consultations, returning not only the best answer, 368 but also those that are related -user consultations are subject to possible imprecision -it is logical to establish a classification based on a certain criterion or group of criteria. This way, the user might 371 obtain not only the object that is more fitted to his consultation but 372 those that are more closely related.…”

Term Weighting: Novel Fuzzy Logic Based Method vs. Classical Tf-Idf Method for Web Information Extraction

“…Step 4: Term weighting See section 4 When a user consultation is made, these term weights are the inputs to a fuzzy logic system, which must detect the object to which the correspondent user consultation refers. System operation is described in (Ropero et al, 2007).…”