Affiliation:
1. G. H. Raisoni College of Engineering, Nagpur, India
Abstract
A considerable amount of time is required to interpret whole news article to get the gist of it. Therefore, in order to reduce the reading and interpretation time, headlines are necessary. The available techniques for news headline construction mainly includes extractive and abstractive headline generation techniques. In this paper, context based news headline is formed from long news article by using techniques of core Natural Language Processing (NLP) and key terms of news article. Key terms are retrieved from lengthy news article by using various approaches of keyword extraction. The keyphrases are picked out using Keyphrase Extraction Algorithm (KEA) which helps to construct headline syntax along with NLP's parsing technique. Sentence compression algorithm helps to generate compressed sentences from generated parse tree of leading sentences. Headline helps user for reducing cognitive burden of reader by reflecting important contents of news. The objective is to frame headline using key terms for reducing reading time and efforts of reader.
Reference26 articles.
1. Atrey, S. H., Prasad, T. V., & Ram Krishna, G. (2012). Issues in parsing and POS tagging of Hybrid Language. In IEEE International Conference on Computational Intelligence and Cybernetics (pp. 20-24).
2. Headline generation based on statistical translation;M.Banko;Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics (ACL ’00), Hong Kong,2000
3. Bohne, T., Rönnau, S., & Borghoff, U. M. (2011). Efficient keyword extraction for meaningful document perception. In Proceedings of the 11th ACM symposium on Document engineering DocEng ‘11.
4. Intelligent Techniques in Signal Processing for Multimedia Security
5. Cross-language headline generation for Hindi