Research Cell: An International Journal of Engineering Sciences

Namita Arora ¹, Jaspreet Kaur Sahiwal ¹, Sanjeev Kumar Sharma ²

Affiliations
1 LPU, Jalndhar, IN
2 B.I.S College of Engineering and Technology, Moga – 142001, IN

Abstract

Organizations be it industry or business or even educational institutes, need to improve their information inventory system so as to survive in the competitive environment. The organizations have to increase their efficiency and effectiveness in maintaining the cycle of activities, in their planning, decision-making processes, and analytical needs. There are several ways to acquire this goal; one of it is with data mining which is able to make a prediction using existing data in their database in order to forecast future demand. All most all the NLP application are based on the data mining techniques. So there is need to apply the data warehouse technique in natural language processing field.

Full Text

   

Gagan Bansal ¹, Satinder Pal Ahuja ¹, Sanjeev Kumar Sharma ²

Affiliations
1 Indo Global College of Engg., Mohali, IN
2 B.I.S College of Engineering and Technology, Moga, IN

Abstract

Morphological analysis is essential for natural language processes like generation of Treebanks, training of parsing models and parsing. Rule based approach is applicable to the languages which have well defined set of rules to accommodate most of the words with inflectional and derivational morphology. Rule based morphological analysis is very difficult and cannot accommodate all combinations through the rules due to inflections and exceptions especially in languages like Punjabi. Statistical methods are very important which in turn need large volume of electronic corpus and automated tools which are not available in Punjabi. Lexicon based morphological analyzer has been developed for Punjabi. This can be further improved by adding new words with their grammatical information.

Full Text

   

Sapna Kanwar ¹, Mr. Ravishankar ², Sanjeev Kumar Sharma ³

Affiliations
1 LPU, Jalandhar, IN
2 LPU, Jalndhar, IN
3 B.I.S College of Engineering and Technology, Moga – 142001, IN

Abstract

POS tagger is the process of assigning a correct tag to each word of the sentence. We attempted to improve the accuracy of existing Punjabi POS tagger. This POS tagger lacks in resolving the ambiguity of compound and complex sentences. A Bi-gram Hidden Markov Model has been used to solve the part of speech tagging problem. An annotated corpus was used for training and estimating of HMM parameter. Maximum likelihood method has been used to estimate the parameter. This HMM approach has been implemented by using Viterby algorithm.

Full Text

   

Blossom Manchanda ¹, Mr. Ravishanker ², Sanjeev Kumar Sharma ³

Affiliations
1 B.I.S College of Engineering and Technology, Moga – 142001, IN
2 LPU, Jalandhar, IN
3 B.I.S College of Engineering and Technology, IN

Abstract

The accuracy of unknown words in the task of Part of Speech tagging is one significant area where there is still room for improvement. Because of their high information content, unknown words are also disproportionately important for how often they occur, and increase in number when experimenting with corpora from different domains. One area however, where all POS tagging methods suffer a significant decrease in accuracy, is with unknown words. These words are those that are seen for the first time in the testing phase of the tagger, having never appeared in the training data. In general, on POS tagging as well as other similar NLP tasks, accuracy on unknown words is about 10% less than words that have been seen in the training data (Brill, 1994). Unknown words also occur a significant amount of the time, comprising approximately 5% of a test corpus (Mikheev, 1997).

Full Text

   

Sanjeev Kumar Sharma ¹, G. S. Lehal ²

Affiliations
1 B.I.S. Engineering College, Kot Ise Khan, Moga, IN
2 Department of Computer Science, Punjabi University, Patiala, IN

Abstract

Compound sentences constitute major parts of the Punjabi language. All the large sentences are either of compound or of complex type. Detail analysis of compound sentences is helpful in processing the Punjabi language through computer. This study will be helpful in identifying and separating the compound sentences from Punjabi corpus. Also this study will be helpful in developing other NLP applications like converting a compound sentence in simple sentences, grammar checking of compound sentences, summarization and machine translation etc.

Full Text

   

Leekha Jindal ¹, Ravinder Jindal ¹, Sanjeev Kumar Sharma ²

Affiliations
1 Research Scholar, SBBS University, Jalandhar, IN
2 Associate Professor, DAV University, Jalandhar, IN

Abstract

Having an error detection and correction system is a fundamental requirement for any word processing application such as MS Word, Applix Word, JWPce, KWord, etc. Despite various efforts to develop such systems using rule-based, statistical-based, and other machine learning approaches, none of them have been satisfactory. The author of this research proposes an algorithm that utilizes the Hidden Markov Model to detect grammatical errors in input sentences. The Viterby algorithm is used to implement the Hidden Markov Model, and an annotated corpus from ILCI is used to calculate the HMM parameters. The results of testing the system on three types of datasets showed an overall precision of 100%, recall of 93.83%, and an f-measure of 96.7. The proposed algorithm has the potential to be used in the development of similar systems for other Indian languages.

Keywords

Grammar Checker, Syntactic Analyzer, Error Detection, HMM.

Full Text

   

Ravinder Mohan Jindal ¹, Leekha Jindal ¹, Sanjeev Kumar Sharma ²

Affiliations
1 Research Scholar, SBBS University, Jalandhar, IN
2 Associate Professor, DAV University, Jalandhar, IN

Abstract

The field of natural language processing is growing in computer science, and generating paraphrases is a difficult task, especially for languages like Hindi, Punjabi, and Urdu, which are morphologically rich and have limited resources. This research article focuses on generating paraphrases for Punjabi, a morphologically rich Indian language, using a sentence simplification approach. The author employed several sentence simplification algorithms to simplify long Punjabi sentences and used antonym-synonym replacement to generate the paraphrases. The sentence simplification component of the system achieved a precision of 100%, recall of 95%, and an f-measure of 97.43% when tested with a set of data. The developed system's performance was analyzed using various complexity measurement parameters, and it was observed that a combination of lexical and syntactic simplifications yielded the best results.

Keywords

NLP, Punjabi Language Processing, Paraphrasing, Syntactic Simplification, Lexical Simplification.

Full Text

   

Deepak Sharma ¹, Sanjeev Kumar Sharma ²

Affiliations
1 Research Scholar, DAV University, Jalandhar, IN
2 Associate Professor, DAV University, Jalandhar, IN

Abstract

Disease detection using soft computing is an emerging field that utilizes various techniques from the domain of artificial intelligence and machine learning to accurately diagnose diseases. Soft computing techniques, such as neural networks, fuzzy logic, and genetic algorithms, are used to build intelligent systems that can analyze complex data and patterns to identify the presence of diseases. In this research paper author has put his efforts to explore the application of soft computing in the diagnosis of disease. Author choose fuzzy logic as the soft computing technique and explore the work done by various researchers for disease diagnosis using fuzzy logic. Author concluded that disease detection using soft computing is a promising area of research that has the potential to transform the field of healthcare. By harnessing the power of artificial intelligence and machine learning, we can improve the accuracy and efficiency of disease diagnosis, leading to better patient outcomes and a healthier society.

Keywords

Soft Computing, Fuzzy Logic, Disease Diagnosis.

Full Text