A Study of Information Retrieval Based on Ontology

DAI+Jin-jing

【Abstract】Focused on the issues which emerged in the traditional search engine that the result can not be satisfying in the precision or in the recall， based on the theory of ontology and so on， pointed out the advantage of using ontology in information retrieral to improve the traditional search engine.

【Key words】ontology； information retrieval

1. Introduction

When talking about Information Retrieval， users are now experiencing huge difficulties in finding precisely what they are looking for， among the tons of documents available. The key problem in achieving efficient and user-satisfactory retrieval is the development of a search mechanism to guarantee delivery of minimal irrelevant information （high precision） while insuring relevant information is not overlooked （high recall）.

Ontology is such a tool that can describe word meanings and relations. Nowadays， ontology is introduced in Information Retrieval System （IRS） for the purpose of solving the problem of semantic understanding.

2. Synopsis of Ontology

Ontology is an explicit， partial account of a conceptualization/ the intended models of a logical language. And also ontology is a semantic foundation communication in different subject （human machine software system etc） of domain internal.

It can promote the data sharing data exchange and knowledge reuse between human with heterogeneous system. It also promotes the automatic or semi-automatic reasoning of intellectual.

3. Thesaurus and Ontology in IR

The traditional IR is based on thesaurus that represents a field of specific knowledge through its conceptual structure. Functions of the thesaurus in IR can be summarized as standardizing users query expression， and adjusting the scope of IR automatically. So new retrieval technology must be reconstructed or introduced into existing information retrieval， namely more exact and faster retrieval tools should be developed.

Compared with thesaurus， ontology has a rich and formal logic-based language for specifying meaning of terms. The conceptual relations represented in ontology are extremely varied and they depend on the field of knowledge to be structured. There is a growing number of voices claiming that the use of ontology for IR is an efficient method that can be superior to others in both precision and relevance.

4. Using Ontology for IR

4.1 explicit specification of a conceptualization

Initially， ontology is introduced as an “explicit specification of a conceptualization”. Therefore， ontology can be used in an integration task to describe the semantics of the information sources and to make the content explicit. With respect to the integration of data sources， they can be used for the identification and association of semantically corresponding information concepts. However， in several projects ontology takes over additional tasks.

4.2 overcoming the limitations of keyword-based search

The use of ontology to overcome the limitations of keyword-based search has been put forward as one of the motivations of the Semantic Web since its emergence in the late 90s. While there have been contributions in this direction in the last few years， most achievements so far either make partial use of the full expressive power of an ontology-based knowledge representation， or are based on Boolean retrieval models， and therefore lack an appropriate ranking model needed for scaling up to massive information sources.

5. Conclusion

An ontology is constructed with the aim of sharing and reusing stored information， which， having been formalized， can be interpreted by both persons and computers.

On the one hand， users information need turns into query expression that computer can read through the shared ontology. Then in order to improve the recall we should expand the queries. This process is also based on the relevant concepts in the shared ontology. On the other hand， the documents should be annotated and indexed through the same ontology. The representation of the documents includes logical assertions that make it an integrated part of the ontological structure. In this way， the matching process can be generalized to， an exploration process that can be implemented in a number of different ways， depending on the form and logical interpretation of the query.

References：

[1]Maedche Staab S.Ontology learning for the semantic web[J].IEEE Intelligent Systems，2001，16（2）：72-79.

[2]Labriji A，Charkaoui S，Abdelbaki I，et al.User interest center based on a semantic user profile[C]//Multimedia Computing and Systems（ICMCS），2016 5th International Conference on.IEEE， 2016：693-696.

[3]Schiessl M，Br?scher M.Ontology lexicalization：Relationship between content and meaning in the context of Information Retrieval[J].Transinforma??o，2017，29（1）：57-72.

作者簡介： 代金晶（1985-）， 女， 貴州銅仁人， 碩士， 貴州師范學院圖書館館員， 主要研究方向為知識管理與數字圖書館。