Papers by KAMAL DEEP GARG
International Journal of Computer Applications, 2013
Complex sentences constitute major parts of the Punjabi language. All the large sentences are eit... more Complex sentences constitute major parts of the Punjabi language. All the large sentences are either of compound or of complex type. Detail analysis of complex sentences is helpful in processing the Punjabi language through computer. This study will be helpful in identifying and separating the complex sentences from Punjabi corpus. Also this study will be helpful in developing other NLP applications like converting a complex sentence in simple sentences, grammar checking of complex sentences, summarization and machine translation etc. Punjabi language is a member of the Indo-Aryan family of languages, also known as Indic languages. Other members of this family are Hindi, Bengali, Gujarati, and Marathi etc. Indo-Aryan languages form a subgroup of the Indo-Iranian group of languages, which in turn belongs to Indo-European family of languages. Punjabi is spoken in India,
Applied Sciences
Machine Translation (MT) systems are now being improved with the use of an ongoing methodology kn... more Machine Translation (MT) systems are now being improved with the use of an ongoing methodology known as Neural Machine Translation (NMT). Natural language processing (NLP) researchers have shown that NMT systems are unable to deal with out-of-vocabulary (OOV) words and multi-word expressions (MWEs) in the text. OOV terms are those that are not currently included in the vocabulary that is used by the NMT system. MWEs are phrases that consist of a minimum of two terms but are treated as a single unit. MWEs have great importance in NLP, linguistic theory, and MT systems. In this article, OOV words and MWEs are handled for the Punjabi to English NMT system. A parallel corpus for Punjabi to English containing MWEs was developed and used to train the different models of NMT. Punjabi is a low-resource language as it lacks the availability of a large parallel corpus for building various NLP tools, and this is an attempt to improve the accuracy of Punjabi in the English NMT system by using n...
DEVELOPMENT, Jul 1, 2011
Machine t ransliteration has gain ed prime importance as a supporting tool for Machine translatio... more Machine t ransliteration has gain ed prime importance as a supporting tool for Machine translation and cross language information retrieval especially when proper names and technical terms are involved. The performance of machine translation and cross-language information retrieval depends extremely on accurate transliteration of named entities. Hence, the transliteration model must aim to preserve the phonetic structure of words as closely as possible. This paper addresses the problem of transliterating Punjabi to English language ...
In the current era internet has become the most important source of information. User can retriev... more In the current era internet has become the most important source of information. User can retrieve data from web about any topic but the effectiveness of retrieval is important factor to be considered. Stemming is an approach to make information systems more effective. Different approaches have been adopted for stemming and in the proposed stemmer a hybrid approach of brute force, suffix substitution and suffix removal algorithm is used. To reduce the problem of over-stemming and under-stemming this stemmer has been proposed. And the accuracy will also be improved to some extent with the help of this proposed hybrid approach.
Transliteration is the conversion of a text from one script to another. It is basically the conve... more Transliteration is the conversion of a text from one script to another. It is basically the conversion of one writing system to another. The characters from a source language are mapped to the characters of the target language. Designing a transliteration system is based on grapheme, phoneme, and correspondence and hybrid methods. In this paper, all these methods will be discussed. The idea is to develop a Bengali to English Machine Transliteration system using rule-based approach. A forward transliteration system for proper nouns, names of cities, states and rivers will be discussed in this paper.
Wireless Sensor Networks (WSNs) are widely used nowadays for seamless data transfer from one sens... more Wireless Sensor Networks (WSNs) are widely used nowadays for seamless data transfer from one sensor node to others using the wireless channel. The term routing means sending the data packets from a source node to the destination node. There exist various routing protocols that ensure the efficient delivery of data from source to destination in terms of distance, energy and Received Signal Strength Indicator etc. In this paper various WSN routing protocols are reviewed to identify gap in study.
International Journal of Engineering Trends and Technology, 2020
Object Detection is a popular field of research for recent technologies. In recent years, profoun... more Object Detection is a popular field of research for recent technologies. In recent years, profound learning performance attracts the researchers to use it in many applications. Number plate (NP) detection and classification is analyzed over decades however, it needs approaches which are more precise and state, language and design independent since cars are now moving from state to another easily. In this paperwe suggest a new strategy to detect NP and comprehend the nation, language and layout of NPs. YOLOv2 sensor with ResNet attribute extractor heart is proposed for NP detection and a brand new convolutional neural network architecture is suggested to classify NPs. The detector achieves average precision of 99.57% and country, language and layout classification precision of 99.33%. The results outperforms the majority of the previous works and can move the area forward toward international NP detection and recognition.
Machine Translation System Using Deep Learning for Punjabi to English
Proceedings of the International Conference on Paradigms of Computing, Communication and Data Sciences, 2021
Web Recommendation by Exploiting User Profile and Collaborative Filtering
Lecture Notes in Electrical Engineering, 2022
A Valuable approach for Image Processing and Change Detection on Synthetic Aperture Radar Data
ABSTRACT In this paper, we proposed an approach for unsupervised change detection technique on SA... more ABSTRACT In this paper, we proposed an approach for unsupervised change detection technique on SAR data. Change detection is process of automatically identifying and analyzing the regions which undergone some changes such as spatial or spectral changes. As various traditional techniques are available to detect change on satellite images. In order to detect change on SAR images we use PCA technique which involve Singular Value Decomposition Method (SVD) method to process the images. After that we compare the images pixel by pixel and find out the changed pixels and map those pixels to display the changed map.
International Journal of Computer Applications, 2011
This paper presents Myanmar phrases translation model with morphology analysis. The system is bas... more This paper presents Myanmar phrases translation model with morphology analysis. The system is based on statistical approach. In statistical machine translation, large amount of information is needed to guide the translation process. When small amount of training data is available, morphological analysis is needed especially for morphology rich language. Myanmar language is inflected language and there are very few creations and researches of corpora in Myanmar, comparing to other language such as English, French, and Czech etc. Therefore, Myanmar phrases translation model is based on syntactic structure and morphology of Myanmar language. Bayes rule is also used to reformulate the translation probability of phrase pairs. Experiment results showed that proposed system can improve translation quality by applying morphological analysis on Myanmar language.
International Journal of Engineering & Technology, 2018
This paper describes the creation process and statistics of Punjabi English (PunEng) parallel cor... more This paper describes the creation process and statistics of Punjabi English (PunEng) parallel corpus. Parallel corpus is the main requirement to develop statistical machine translation as well as neural machine translation. Until now, we do not have any availability of PunEng parallel corpus. In this paper, we have shown difficulties and intensive labor to develop parallel corpus. Methods used for collecting data and the results are discussed, errors during the process of collecting data and how to handle these errors will be described.
Spell checker is a program used for examining the spelling errors and also improving that faults ... more Spell checker is a program used for examining the spelling errors and also improving that faults in the text or a document. Spell checker is a platform which is used to identify the words which are misspelled and update the user about those misspelled words. It depend on the components of spell checker either to spontaneously accurate the misspelled word or ask the user to select the right word from the recommendations which are existing for that specific misspelled word. Spell checker may be an operation which has ability of functioning on a huge part of text or as an element of larger application such as text editor, email, blog writing, keyword searching. Developing a spell checker for Indian languages such as Punjabi, Hindi and Oria etc. step-up several new problems which are not faced in English, which makes the design of spell checker very challenging. The very first constraint for developing any spell checker is to have dictionary of different words of that language which will work as word list. This paper survey the different available spell checker for Indian language (Hindi and Punjabi) and their approach used to detect and correct spell errors.
This paper describes the creation process and statistics of Punjabi English (PunEng) parallel cor... more This paper describes the creation process and statistics of Punjabi English (PunEng) parallel corpus. Parallel corpus is the main requirement to develop statistical machine translation as well as neural machine translation. Until now, we do not have any availability of Pu-nEng parallel corpus. In this paper, we have shown difficulties and intensive labor to develop parallel corpus. Methods used for collecting data and the results are discussed, errors during the process of collecting data and how to handle these errors will be described.
Stemming is the process of automatic removal of affixes from the word without doing complete morp... more Stemming is the process of automatic removal of affixes from the word without doing complete morphological analysis. In this process the word having the same stem are reduced to the common form. Stemming is the very first phase of any information retrieval task such as Text Summarization, Word sense disambiguation etc. Also find its use in the search engine optimization so as to reduce the query processing time. The paper presents the Enhanced Punjabi Stemmer which is based on hybridization of the two major algorithms used in Punjabi stemmer so far that are Look up table Algorithm and Rule based algorithm for suffix removal. Synset approach is also incorporated in the stemmer so as to return the list of words that share the same meaning with the valid stem word. A large database will be used so as to improve the accuracy level of the Stemmer
Spell checker is a tool used for checking the spelling errors and also correcting those errors in... more Spell checker is a tool used for checking the spelling errors and also correcting those errors in the text or a document. Grammar checker is a program which is used to verify the grammatical errors in the text. Developing a spell checker and grammar checker for Indian languages such as Punjabi raises many new difficulties which are not in English, which makes the design of spell checker and grammar checker very difficult. The main difficulties faced are-there is no basic layout of Punjabi keyboard and also there is no approved format for Punjabi spellings. There are lots of differences in grammatical properties of Punjabi that makes it different from other languages. Punjabi is the world's 12th most widely spoken language. The very first requirement for developing any spell checker is to have dictionary of different words of that language which will work as lexicon. The paper aims to develop a system which is hybrid combination of spell checker and grammar checker for Punjabi. Firstly the system checks for spelling errors, then checks for grammatical errors in the text. When some input text is given to system, it is passed through spelling checker and then grammar checker. A comparative, efficient algorithm has been proposed which is hybrid combination of spell checker and grammar checker for Punjabi which saves time and cost.
Complex sentences constitute major parts of the Punjabi language. All the large sentences are eit... more Complex sentences constitute major parts of the Punjabi language. All the large sentences are either of compound or of complex type. Detail analysis of complex sentences is helpful in processing the Punjabi language through computer. This study will be helpful in identifying and separating the complex sentences from Punjabi corpus. Also this study will be helpful in developing other NLP applications like converting a complex sentence in simple sentences, grammar checking of complex sentences, summarization and machine translation etc.
In the current era internet has become the most important source of information. User can retriev... more In the current era internet has become the most important source of information. User can retrieve data from web about any topic but the effectiveness of retrieval is important factor to be considered. Stemming is an approach to make information systems more effective. Different approaches have been adopted for stemming and in the proposed stemmer a hybrid approach of brute force, suffix substitution and suffix removal algorithm is used. To reduce the problem of over-stemming and under-stemming this stemmer has been proposed. And the accuracy will also be improved to some extent with the help of this proposed hybrid approach.
Machine transliteration deals with the conversion of one source language to its corresponding tar... more Machine transliteration deals with the conversion of one source language to its corresponding target language. The languages involved can be either identical type like English-French pair or dissimilar type like English-Bengali pairs. It generally is the mapping of one alphabet from a source language to its corresponding target alphabet. It helps in bridging the gap between machines and natural language understanding. This paper deals with the various machine transliteration systems that have been developed, their methods and approaches.
Uploads
Papers by KAMAL DEEP GARG