Search for Appropriate Textual Information Sources

Abstract

In this paper, we deal with the support in the search for appropriate textual sources. Users ask for an atomic concept that is explicated using machine learning methods applied to different textual sources. Next, we deal with the so-obtained explications to provide even more useful information. To this end, we apply the method of computing association rules. The method is one of the data-mining methods used for information retrieval. Our background theory is the system of Transparent Intensional Logic (TIL); all the concepts are formalised as TIL constructions.

Conceptual Framework for the Conversion of Text Document into TIL-Script

“…It is a project which is developing cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. 7 The annotation scheme is based on an evolution of (universal) Stanford dependencies see [23], Google universal part-ofspeech tags, see [24], and the Interset interlingua for morphosyntactic tagsets, see [25].…”

“…This part was introduced in [1], [2], [3]. The second part concerns machine learning and searching for relevant text sources which was introduces in [4], [5], [6], [7]. Now our system presuppose that all the inputs are transformed into TIL-Script.…”

Improvement of Searching for Appropriate Textual Information Sources Using Association Rules and FCA

“…As an example of recommending relevant information sources based on FCA, we use the same dataset we used in [2]. In our example, we used text sources dealing with the concept of wild cat.…”

“…In case of studying certain problematic area, we need to acquire a list of appropriate papers we want to study to have the whole picture of a particular problem. Therefore in [1], [2] and [3], we introduced methods, where we utilize the methods of Association Rules and the Relevant Ordering based on the Formal Concept Analysis as a theoretical background for selecting the most relevant text-sources. Those methods are based on applying the theory of machine learning and concept explications (more in [4]).…”

“…The complete process of finding the set of recommended text sources is demonstrated by an example. For a clear comparison, we used the same example as in [2] and [3]. We point at some problems which might occur using our methods in combination with Iceberg Concepts.…”