Search results

1 – 4 of 4
Article
Publication date: 1 March 1998

Robert Gaizauskas and Yorick Wilks

In this paper we give a synoptic view of the growth of the text processing technology of information extraction (IE) whose function is to extract information about a pre‐specified…

1390

Abstract

In this paper we give a synoptic view of the growth of the text processing technology of information extraction (IE) whose function is to extract information about a pre‐specified set of entities, relations or events from natural language texts and to record this information in structured representations called templates. Here we describe the nature of the IE task, review the history of the area from its origins in AI work in the 1960s and 70s till the present, discuss the techniques being used to carry out the task, describe application areas where IE systems are or are about to be at work, and conclude with a discussion of the challenges facing the area. What emerges is a picture of an exciting new text processing technology with a host of new applications, both on its own and in conjunction with other technologies, such as information retrieval, machine translation and data mining.

Details

Journal of Documentation, vol. 54 no. 1
Type: Research Article
ISSN: 0022-0418

Keywords

Article
Publication date: 1 April 1994

Yorick Wilks

The paper argues that the IBM statistical approach to machine translation has done rather better after a few years than many sceptics believed it could. However, it is neither as…

Abstract

The paper argues that the IBM statistical approach to machine translation has done rather better after a few years than many sceptics believed it could. However, it is neither as novel as its proponents suggest nor is it making claims as clear and simple as they would have us believe. The performance of the purely statistical system (and we discuss what that phrase could mean) has not equalled the performance of SYSTRAN. More importantly, the system is now being shifted to a hybrid that incorporates much of the linguistic information that it was initially claimed by IBM would not be needed for MT. Hence, one might infer that its own proponents do not believe ‘pure’ statistics sufficient for MT of a usable quality. In addition to real limits on the statistical method, there are also strong economic limits imposed by their methodology of data gathering. However, the paper concludes that the IBM group have done the field a great service in pushing these methods far further than before, and by reminding everyone of the virtues of empiricism in the field and the need for large scale gathering of data.

Details

Aslib Proceedings, vol. 46 no. 4
Type: Research Article
ISSN: 0001-253X

Content available
Article
Publication date: 1 July 1999

D.M. Hutton

59

Abstract

Details

Kybernetes, vol. 28 no. 5
Type: Research Article
ISSN: 0368-492X

Keywords

Article
Publication date: 1 October 2005

Hamish Cunningham, Kalina Bontcheva and Yaoyong Li

Seeks to explore the gap that exists between knowledge management (KM) systems and the natural language materials that form almost all corporate data stores.

2597

Abstract

Purpose

Seeks to explore the gap that exists between knowledge management (KM) systems and the natural language materials that form almost all corporate data stores.

Design/methodology/approach

A conceptual discussion and approach are taken using recent scientific results in the fields of the semantic web and ontology‐based information extraction.

Findings

Provides a high‐level introduction to information extraction (IE) and descriptions of application scenarios for KM tools that exploit IE, a form of natural language analysis to link semantic web models with documents. The paper presents some examples of ontology‐based IE systems, one of which, KIM, is under development in the SEKT Project. KIM offers IE‐based facilities for metadata creation, storage and conceptual search. The system can be used by diverse applications for annotating and querying documents.

Originality/value

Focuses on technologies and facilities that will become an important part of next‐generation KM applications.

Details

Journal of Knowledge Management, vol. 9 no. 5
Type: Research Article
ISSN: 1367-3270

Keywords

Access

Year

Content type

Article (4)
1 – 4 of 4