AUTOMATIC EXTRACTION OF ACRONYMS FROM ENGLISH NEWSPAPERS

Acronyms are one type of abbreviations used in scientific and ordinary newspapers for enhancing readability and also to reduce typing overhead. This paper concentrates on the automatic detection and extraction of acronym definition pairs, which allows the building of acronym lists and appears to be central to acronym based tool-building. This paper explains how the acronym expansion varies with the domain and geography. This paper also presents a simple version of acronym naming pattern learning and storing these patterns for quick identification of possible expansion when it is not present in original text. Our techniques are also evaluated on material from the English newspaper websites (http://www.the hindu.com/ and https://economictimes.indiatimes. com). The program that implements these techniques is written in python and NLTK and tested.