P
P. C. Reghu Raj
Researcher at Government Engineering College, Sreekrishnapuram
Publications - 33
Citations - 160
P. C. Reghu Raj is an academic researcher from Government Engineering College, Sreekrishnapuram. The author has contributed to research in topics: Malayalam & Natural language. The author has an hindex of 7, co-authored 31 publications receiving 132 citations. Previous affiliations of P. C. Reghu Raj include Indian Institute of Technology Madras.
Papers
More filters
Journal ArticleDOI
Summarization and categorization of text data in high-level data cleaning for information retrieval
TL;DR: A text-mining framework is proposed in which subsystems of a classification system are treated as constituents of a knowledge discovery process for text corpora, and whether there exists a synergic relation between systems for classification and those for summarization by way of composing those subsystems is explored.
Proceedings ArticleDOI
Fuzzy logic based hybrid approach for sentiment analysisl of Malayalam movie reviews
TL;DR: A hybrid approach for Sentiment Analysis is used in which Machine Learning method is used for tagging and Fuzzy Logic is used to find the membership of the review in each sentiment class.
Proceedings ArticleDOI
N-gram based algorithm for distinguishing between Hindi and Sanskrit texts
TL;DR: This paper presents an N-gram based method of language identification for documents written in Hindi and Sanskrit, which have the same script and the results are shown.
Journal ArticleDOI
Unsupervised Approach to Word Sense Disambiguation in Malayalam
TL;DR: The aim of this work is to develop a WSD system for Malayalam, a language spoken in India, predominantly used in the state of Kerala, which uses a corpus which is collected from variousMalayalam web documents.
Proceedings ArticleDOI
Random forest algorithm for improving the performance of speech/non-speech detection
TL;DR: This work experimented with the use of time domain, frequency domain and cepstral domain features for short time frames of 20 ms, and observed that correlation based feature selection gave the best results.