Integrating knowledge from different sources for automatic back-of-the-book indexing
نویسنده
چکیده
The paper reports research on automatic back-of-the-book indexing. It presents a methodology which brings together knowledge from different disciplines. It is inspired by human indexing methodology and the results are more similar to manually-crafted indexes than those produced by previous automatic approaches. Issues of evaluation and applications are addressed. Résumé : Cette communication présente les résultats de recherche sur l'indexation automatique de livres. L'étude propose une méthodologie qui rassemble des sources de connaissances provenant de disciplines différentes. La méthodologie s'inspire de l'indexation humaine et les résultats se rapprochent plus de l'indexation manuelle que les autres méthodes d'indexation automatique. Sont également touchés les enjeux d'évaluation et d'applicabilité.
منابع مشابه
Investigating the Extent of Correspondence between the Persian Book Final Indices and ISO 999 and B.S. 3700 Standards: The Case of the Field of Library and Information Sciences
Background and Aim: The purpose of this study was to investigate the extent of observing the standards of indexing (ISO 999-1996, BS 3700) of Library and Information Sciences books. Method: The study used descriptive-analytical methodology and the population consisted of all the Persian books, written and translated, in the field of Library and Information Sciences published from 2006 to 2012 w...
متن کاملSyntactic Approaches to Automatic Book Indexing
Automatic book indexing systems are based on the generation of phrase structures capable of reflecting text content. • Some approaches are given for the automatic construction of back-of-book indexes using a syntactic analysis of the available texts, followed by the identification of nominal constructions, the assignment of importance weights to the term phrases, and the choice of phrases as in...
متن کاملA study of the principles and categories related to the world of architecture in the book of Nuzhat Nama-yi Ala'i
Ancient Persian sources are among the most important sources for understanding the past architecture of Iran. Among these texts is the book Nuzhat Nama-yi Alachr('39')i by Shah Mardan Ibn Abi al-Khayr, which was written in the last years of the fifth century AH. This book is an encyclopedia of common sciences of that time and includes various subjects such as animals, plants, jewelry, arithmeti...
متن کاملمدل دو مرحله ای شکاف- گلچین برای نمایه سازی خودکار متون فارسی
Purpose: Each language has its own problems. This leads to consider appropriate models for automatic indexing of every language. These models should concern the exhaustificity and specificity of indexing. This paper aims at introduction and evaluation of a model which is suited for Persian automatic indexing. This model suggests to break the text into the particles of candidate terms and to c...
متن کاملAutomatic Hashtag Recommendation in Social Networking and Microblogging Platforms Using a Knowledge-Intensive Content-based Approach
In social networking/microblogging environments, #tag is often used for categorizing messages and marking their key points. Also, since some social networks such as twitter apply restrictions on the number of characters in messages, #tags can serve as a useful tool for helping users express their messages. In this paper, a new knowledge-intensive content-based #tag recommendation system is intr...
متن کامل