RT Journal Article
T1 Text Summarization Technique for Punjabi Language Using Neural Networks
A1 Jain, Arti
A1 Arora, Anuja
A1 Yadav, Divakar
A1 Morato Lara, Jorge Luis
A1 Kaur, Amanpreet
AB In the contemporary world, utilization of digital content has risen exponentially. For example, newspaper and webarticles, status updates, advertisements etc. have become an integral part of our daily routine. Thus, there is a need to buildan automated system to summarize such large documents of text in order to save time and effort. Although, there aresummarizers for languages such as English since the work has started in the 1950s and at present has led it up to a maturedstage but there are several languages that still need special attention such as Punjabi language. The Punjabi language ishighly rich in morphological structure as compared to English and other foreign languages. In this work, we provide threephase extractive summarization methodology using neural networks. It induces compendious summary of Punjabi single textdocument. The methodology incorporates pre-processing phase that cleans the text; processing phase that extracts statisticaland linguistic features; and classification phase. The classification based neural network applies an activation function-sigmoid and weighted error reduction-gradient descent optimization to generate the resultant output summary. The proposedsummarization system is applied over monolingual Punjabi text corpus from Indian languages corpora initiative phase-II.The precision, recall and F-measure are achieved as 90.0%, 89.28% an 89.65% respectively which is reasonably good incomparison to the performance of other existing Indian languages" summarizers.
PB IAJIT
SN 1683-3198
YR 2021
FD 2021-11-01
LK https://hdl.handle.net/10016/37752
UL https://hdl.handle.net/10016/37752
LA eng
NO This research is partially funded by the Ministry of Economy, Industry and Competitiveness,  Spain (CSO2017-86747-R).
DS e-Archivo
RD 15 may. 2024