Knowledge Based Approach

The quick increment in the online data content has made it extremely troublesome for individuals to discover data that is pertinent to their requirements and interests. Proposal framework is an intense apparatus that gives a potential answer for this test by offering a mechanized component to search out applicable and new data. Individuals depend on client surveys on the web when they require data about item, motion picture, video, news, eatery, and so on. In any case, fundamental issue is giving suggestion to client shape huge information environment. Huge information is a rising innovation, as the name recommends is about taking care of huge measure of information, technique and preparing the information inside middle of the road passed time. An enormous information is gathered and handled to settle on some choice furthermore used to portray any sort of information which might be organized, semi-organized, unstructured and if the information develops. In this work our primary commitment is to prescribe online recordings to client in view of client intrigue. In past framework, recordings were positioned in view of the viewer of that video yet in our proposed framework recordings are positioned and prescribed to client in view of remarks, check and likes. Here client can give remarks just in the event that he/she has watched that specific video, generally clients are not qualified to give remarks on that video. By the assistance of this element we rank recordings in remarks and likes based. The upgrade of our proposition is the opinion grouping of client remarks, with two conceivable marks: negative (neg) and positive (pos). The given technique is utilized to enhance the versatility and effectiveness, if information develops.

The knowledge-based approach of the PE subject involves the achievement of a mix between a theoretical and a practical component. This approach aims to provide the student with the necessary theoretical notions for an in-depth understanding of the role that practical activity plays in maintaining health. In this way, PE

The knowledge-based approach of the PE subject involves the achievement of a mix between a theoretical and a practical component. This approach aims to provide the student with the necessary theoretical notions for an in-depth understanding of the role that practical activity plays in maintaining health. In this way, PE becomes a meaningful school subject for the student. Aim: This paper aims at testing the following hypotheses, built on the conclusions of previous studies: (1) PE teachers consider the theoretical content as less important than the practical one; (2) teachers would rather not deal with the implementation of theoretical content. Method: A data collection tool was devised taking as reference a group of 210 PE teachers, selected by mixed randomization from 7 counties of Romania. The obtained data were then analysed using the statistical programming language R (see 4.1.3). Results and discussions: Teachers value practical content more (4.948) than theoretical content (4.082). And we find this difference even after analysing the data according to the seniority of the teachers within the department. The lowest value is recorded when teachers were asked for their opinion related to the necessity of a PE textbook (3.063). Conclusions and future implications: The two components (theoretical and practical) are not equally appreciated by specialized teachers. This fact highlights the need to emphasise the role of theoretical knowledge within the PE lesson in the training of future teachers.

The knowledge-based approach of the PE subject involves the achievement of a mix between a theoretical and a practical component. This approach aims to provide the student with the necessary theoretical notions for an in-depth understanding of the role that practical activity plays in maintaining health. In this way, PE becomes a meaningful school subject for the student. Aim: This paper aims at testing the following hypotheses, built on the conclusions of previous studies: (1) PE teachers consider the theoretical content as less important than the practical one; (2) teachers would rather not deal with the implementation of theoretical content. Method: A data collection tool was devised taking as reference a group of 210 PE teachers, selected by mixed randomization from 7 counties of Romania. The obtained data were then analysed using the statistical programming language R (see 4.1.3). Results and discussions: Teachers value practical content more (4.948) than theoretical content (4.082). And we find this difference even after analysing the data according to the seniority of the teachers within the department. The lowest value is recorded when teachers were asked for their opinion related to the necessity of a PE textbook (3.063). Conclusions and future implications: The two components (theoretical and practical) are not equally appreciated by specialized teachers. This fact highlights the need to emphasise the role of theoretical knowledge within the PE lesson in the training of future teachers.

This work aims to integrate the tactical and operational decision making levels. A typical Scheduling mixed integer linear programming (MILP) model has been solved using several demand scenarios. The results have been analyzed and accordingly the operation cost vs. production levels nonlinear equations have been obtained. The aforementioned equations have been included as constraints of the SC planning problem. Hence, production, inventory and distribution variables along the complete SC have been optimized using a NLP model.

Sentiment analysis is mainly concerned with identifying and classifying opinions or emotions that are expressed within a text. These days, sharing opinions and expressing emotions through social networking websites has become very common. Therefore, a large amount of data is generated each day, on which mining can be effectively performed to retrieve quality information. Sentiment analysis on such data can prove to be instrumental in generating an aggregated opinion on certain products. Twitter sentiment analysis often becomes a difficult task due to the presence of slangs and misspellings. Also, we constantly encounter new words, which makes it more difficult to analyze and compute the sentiment as compared to the usual sentiment analysis. Twitter restricts the length of a tweet to 140 characters. Thus, extracting valuable information from short texts is yet another challenge. Knowledge-based approach and

Context: Knowledge management technologies have been employed across software engineering activities for more than two decades. Knowledge-based approaches can be used to facilitate software architecting activities (e.g., architectural evaluation). However, there is no comprehensive understanding on how various knowledge-based approaches (e.g., knowledge reuse) are employed in software architecture. Objective: This work aims to collect studies on the application of knowledge-based approaches in software architecture and make a classification and thematic analysis on these studies, in order to identify the gaps in the existing application of knowledge-based approaches to various architecting activities, and promising research directions. Method: A systematic mapping study is conducted for identifying and analyzing the application of knowledge-based approaches in software architecture, covering the papers from major databases, journals, conferences, and workshops, published between January 2000 and March 2011. Results: Fifty-five studies were selected and classified according to the architecting activities they contribute to and the knowledge-based approaches employed. Knowledge capture and representation (e.g., using an ontology to describe architectural elements and their relationships) is the most popular approach employed in architecting activities. Knowledge recovery (e.g., documenting past architectural design decisions) is an ignored approach that is seldom used in software architecture. Knowledge-based approaches are mostly used in architectural evaluation, while receive the least attention in architecture impact analysis and architectural implementation. Conclusions: The study results show an increased interest in the application of knowledge-based approaches in software architecture in recent years. A number of knowledge-based approaches, including knowledge capture and representation, reuse, sharing, recovery, and reasoning, have been employed in a spectrum of architecting activities. Knowledge-based approaches have been applied to a wide range of application domains, among which ''Embedded software'' has received the most attention.

Conceptual - Machine learning is the subset of man-made reasoning that goes under information science. Without expressly customized, getting PCs to learn is a science known as Machine Learning. The proposal frameworks present in the market are believed to be working in popular applications like YouTube web-based media applications like Facebook, Instagram or item based applications like Flipkart. Essentially, these frameworks help to focus on data that is concerned or valuable for a specific client. One area where such frameworks can be exceptionally helpful is infection cautioning system. In light of an illness the client contributions to the framework, that he thinks they are inclined to or they are experiencing they will be proposed top 5 or top 3 sicknesses they are generally inclined to dependent on the likeness between the infection client inputted and the illness client is being suggested for this situation being cautioned. As of now, everything is accessible on the web, each...

Internet based recruiting platforms decrease advertisement cost, but they suffer from information overload problem. The job recommendation systems (JRS) have achieved success in e-recruitment process but still they are not able to capture the complexity of matching between candidates’ desires and organizations’ requirements. Thus, we propose a hybrid JRS which combines recommendations of content-based filtering (CBF) and collaborative filtering (CF) to overcome their individual major shortcomings namely overspecialization and over-fitting. In proposed system, CBF model makes recommendations based on candidates’ skills identified from past jobs in which they have applied and CF model makes recommendations based on jobs in which similar users have applied and also those jobs in which that user has applied frequently together in very similar contexts using Word2Vec’s skip-gram model. We used k-Nearest Neighbors technique and Pearson Correlation Coefficient. The recall of our proposed m...

Automatic and accurate detection of the closure-burst transition events of stops and affricates serves many applications in speech processing. A temporal measure named the plosion index is proposed to detect such events, which are characterized by an abrupt increase in energy. Using the maxima of the pitch-synchronous normalized cross correlation as an additional temporal feature, a rule-based algorithm is designed that aims at selecting only those events associated with the closure-burst transitions of stops and affricates. The performance of the algorithm, characterized by receiver operating characteristic curves and temporal accuracy, is evaluated using the labeled closure-burst transitions of stops and affricates of the entire TIMIT test and training databases. The robustness of the algorithm is studied with respect to global white and babble noise as well as local noise using the TIMIT test set and on telephone quality speech using the NTIMIT test set. For these experiments, th...

This work aims to integrate the tactical and operational decision making levels. A typical Scheduling mixed integer linear programming (MILP) model has been solved using several demand scenarios. The results have been analyzed and accordingly the operation cost vs. production levels nonlinear equations have been obtained. The aforementioned equations have been included as constraints of the SC planning problem. Hence, production, inventory and distribution variables along the complete SC have been optimized using a NLP model.

Sentiment analysis is mainly concerned with identifying and classifying opinions or emotions that are expressed within a text. These days, sharing opinions and expressing emotions through social networking websites has become very common. Therefore, a large amount of data is generated each day, on which mining can be effectively performed to retrieve quality information. Sentiment analysis on such data can prove to be instrumental in generating an aggregated opinion on certain products. Twitter sentiment analysis often becomes a difficult task due to the presence of slangs and misspellings. Also, we constantly encounter new words, which makes it more difficult to analyze and compute the sentiment as compared to the usual sentiment analysis. Twitter restricts the length of a tweet to 140 characters. Thus, extracting valuable information from short texts is yet another challenge. Knowledge-based approach and

Sentiment analysis is mainly concerned with identifying and classifying opinions or emotions that are expressed within a text. These days, sharing opinions and expressing emotions through social networking websites has become very common. Therefore, a large amount of data is generated each day, on which mining can be effectively performed to retrieve quality information. Sentiment analysis on such data can prove to be instrumental in generating an aggregated opinion on certain products. Twitter sentiment analysis often becomes a difficult task due to the presence of slangs and misspellings. Also, we constantly encounter new words, which makes it more difficult to analyze and compute the sentiment as compared to the usual sentiment analysis. Twitter restricts the length of a tweet to 140 characters. Thus, extracting valuable information from short texts is yet another challenge. Knowledge-based approach and

WordNet is a crucial resource that aids in several Natural Language Processing (NLP) tasks. The WordNet development activity for 18 Indian languages has been initiated in INDIA by the IndoWordNet1 consortium using the expansion approach with the Hindi WordNet developed by IIT Bombay, as the source. After linking 20K synsets, it was decided that each of these languages should find the coverage of their respective language WordNets by using sense marker tool released by IIT Bombay. The sense marking activity mainly helped in validation of WordNet and improving the WordNet coverage. In this paper, the various effects that sense marking activity had on the Konkani2 language WordNet development are presented.

In this paper we describe a knowledge-based approach that enables the subjective evaluation of portal and e-service quality by users in an adaptive manner. The model for adaptive quality measurement (MAQM) comprises different ontologies including concepts regarding quality aspects, questions and questionnaires, portal characteristics and problems encountered by users while using the portal. A prototype adaptive questionnaire system (SALT) which uses the MAQM model is also described. The system applies three axes of adaptation: based on real-time feedback from users through questionnaires, based on problems encountered by the user and based on metadata of the pages visited by the user. The results of evaluating SALT, compared to a static questionnaire, in an Austrian e-Government portal, are indicative of the value added of our approach.

The recent research work for addressed to the aims at a spectrum of item ranking techniques that would generate recommendations with far more aggregate variability across all users while retaining comparable levels of recommendation accuracy. Individual users and companies are increasingly relying on recommender systems to provide information on individual suggestions. The recommended technologies are becoming increasingly efficient because they are focusing on scalable sorting-based heuristics that make decisions based solely on "local" data (i.e., only on the candidate items of each user) rather than having to keep track of "national" data, such as items have been all user recommended at the time. The real-world rating datasets and various assessments to be the prediction techniques and comprehensive empirical research consistently demonstrate the proposed techniques' diversity gains. Although the suggested approaches have primarily concentrated on improving recommendation accuracy, other critical aspects of recommendation quality, such as recommendation delivery, have often been ignored.

The recent research work for addressed to the aims at a spectrum of item ranking techniques that would generate recommendations with far more aggregate variability across all users while retaining comparable levels of recommendation accuracy. Individual users and companies are increasingly relying on recommender systems to provide information on individual suggestions. The recommended technologies are becoming increasingly efficient because they are focusing on scalable sorting-based heuristics that make decisions based solely on "local" data (i.e., only on the candidate items of each user) rather than having to keep track of "national" data, such as items have been all user recommended at the time. The real-world rating datasets and various assessments to be the prediction techniques and comprehensive empirical research consistently demonstrate the proposed techniques' diversity gains. Although the suggested approaches have primarily concentrated on improving recommendation accuracy, other critical aspects of recommendation quality, such as recommendation delivery, have often been ignored.

We build up a novel structure, named as l-injection, to address the sparsity issue of recommender frameworks. Via precisely infusing low esteems to a chose set of unrated client thing sets in a client thing framework, we show that best N proposal correctness’s of different community oriented separating (CF) systems can be altogether and reliably moved forward. We initially embrace the thought of pre-utilize inclinations of clients toward a tremendous measure of unrated things. Utilizing this thought, we distinguish uninteresting things that have not been evaluated yet but rather are probably going to get low appraisals from clients, and specifically ascribe them as low esteems. As our proposed approach is technique rationalist, it can be effectively connected to an assortment of CF calculations. Through extensive investigations with three genuine datasets (e.g., Movielens, Ciao, and Watcha), we show that our answer reliably and generally upgrades the exactnesses of existing CF calcu...

By and large, searching for work while examining a rundown of enlisting positions on enrollment locales, which truly cost a lot of time and cash is an irritating thing to do Although most of the time those jobs are not always suitable with users, or users are not satisfy. By doing this, recruiters waste their time by making sure that they are qualify or not. This paper seeks to address a very important issue on the recruitment process which is about matching jobs seekers with jobs offers. These days, the coordinating procedure between the candidate and the activity offers is one of the serious issue's organizations need to deal with. Short listing candidates and screening resumes are long time-consuming tasks for the company, especially when 80 percent to 90 percent of the resumes received for a role are unquailed. We have designed and proposed a hybrid personalized recommender system used for job seeking and online recruiting websites adapted to the cold start problem using a collaborating predictive algorithm. The hybrid system is composed of Content-Based filtering as well as Knowledge-based Approach which will be has been coded using the Python language. Precise Recommender Systems are very important nowadays.

A word may have multiple senses and the challenge is to find out which particular sense is appropriate in a given context. Word sense disambiguation(WSD) resolves this ambiguity by finding out which particular sense of a word is appropriate in a given context. WSD is of critical importance in the areas of machine translation, information retrieval, speech processing etc. In this paper we present some approaches to Word sense disambiguation in Nepali using Nepali WordNet. These approaches are overlap based approach and conceptual distance and semantic graph based approach which falls under Knowledge based approach. Conceptual distance and semantic graph distance are used as a measures to score our WSD algorithm.

Hindi is the widely used spoken language in the Indian subcontinent, and is used by more than 260 million Indians citizens. Indian governments has many digital initiatives to serve Indian citizen better, hence Hindi language becomes one of the important languages to serve Indian citizen. The Government initiatives are like smart city, Hospital Services, Common Service Centers, Digital Payment Ecosystem, Pensioners Scheme, Digital Locker and many more. These all initiative are served using mobile and web based applications, which citizens can access easily instead of visiting various government departments. To serve the large Hindi speaking population, it is necessary to handle the ambiguous words which have multiple connotations in any natural language processing task. In this paper, word sense disambiguation for Hindi language is proposed. Proposed method makes use of Lesk algorithm to disambiguate the Hindi words. Novel scoring method is used to assign a sense score to each token ...

— Word sense disambiguation (WSD) is a linguistically based mechanism for automatically defining the correct sense of a word in the context. WSD is a long standing problem in computational linguistics. A particular word may have different meanings in different contexts. For human beings, it is easy to extract the correct meaning by analyzing the sentences. In the area of natural language processing, we are trying to simulate all of these human capabilities with a computer system. In many natural language processing tasks such as machine translation, information retrieval etc., Word Sense Disambiguation plays an important role to improve the quality of systems. Here, I am presenting a survey on WSD that will help users for choosing appropriate algorithms for their specific applications. I.

Resolution of lexical ambiguity, commonly known as Word Sense Disambiguation (WSD) task is to distinguish the correct sense among the set of senses for an ambiguous term depending on the particular context automatically. It plays the vital role as it acts as an intermediate phase to many Natural Language Processing (NLP) applications like Machine Translation, Information Retrieval, Speech Processing, Hypertext navigation, Parts-of -Speech tagging. Existing literature reveals that there are various approaches for lexical ambiguity resolution-Knowledge based, Corpus based. In recent years, many WSD systems is being developed in Indian languages like Hindi, Malayalam, Manipuri, Nepali, Kannada but no such automated system has yet emerged for the Indo-Aryan language- Assamese. Our future work aims to develop a model for the WSD problem which is fast, optimal and efficient in terms of accuracy and scalability. This paper presents a survey report made in this research topic discussing the...

The task of Word Sense Disambiguation (WSD) incorporates in its definition the role of ‘context’. We present our work on the development of a tool which allows for automatic acquisition and ranking of ‘context clues’ for WSD. These clue words are extracted from the contexts of words appearing in a large monolingual corpus. These mined collection of contextual clues form a discrimination net in the sense that for targeted WSD, navigation of the net leads to the correct sense of a word given its context. Utilizing this resource we intend to develop efficient and light weight WSD based on look up and navigation of memory-resident knowledge base, thereby avoiding heavy computation which often prevents incorporation of any serious WSD in MT and search. The need for large quantities of sense marked data too can be reduced.

Current state-of-the-art Word Sense Disambiguation (WSD) algorithms are mostly supervised and use the P (Sense|W ord) statistic for annotation. This P (Sense|W ord) statistic is obtained after training the model on an annotated corpus. The performance of WSD algorithms do not match the efficiency and quality of human annotation. It is therefore important to know the role of the contextual clues in WSD. Human beings in turn, actuate the task of disambiguating the sense of a word, by gathering hints from the context words in the neighbourhood of the word. Contextual clues thus form the basic building block for the human sense disambiguation task. The need was thus felt for a tool, which could help us get a deeper insight into the human mind, while disambiguating polysemous words. As mentioned earlier, in the human mind, sense disambiguation highly depends on finding clues in corpus text, which finally lead to a winner sense. In order to make WSD algorithms more efficient, it is highly desirable to assimilate knowledge regarding contextual clues of words. In order to make WSD algorithms more efficient, it is highly desirable to assimilate knowledge regarding contextual clues of words, which aid in finding correct senses of words in that context. Hence, we developed a tool which could help a lexicographer mark the clues for disambiguating a word in a context. In the current phase, this tool lets the lexicographer select the clues from the gloss and example fields in the synset, and adds them to a database.

Sense Disambiguation" of a word is a simple way of selecting proper sense (meaning) for an ambiguous word in a given context. Sense disambiguation of a word is very crucial, and its importance is used in every application of computational linguistics. There are many methods available in Natural Language Processing for performing the sense disambiguation. In our work, we are proposing the Graph-based algorithm through which the ambiguity is resolved for the words based on their senses and the context domain. Graph-based algorithm creates a graph comprising the word to be disambiguated along with their corresponding candidate sense. In the proposed work, sense disambiguation of word has been done for Marathi language words. Multiple meanings of Marathi word has been explored with the help of Marathi WordNet [4] prepared by IIT-Bombay.

In this paper, we have presented a detailed overview of the Word Sense disambiguation (WSD) efforts undertaken in India related to Indian Languages. Also in remaining sections we have discussed the method used by us for Marathi LanguageWSD. This approach of WSD uses combination of Rules to disambiguate a word to provide a suitable sense with respect to the context.

Word Sense Disambiguation (WSD) is one of the open problems in the area of natural language processing. Various supervised, unsupervised and knowledge based approaches have been proposed for automatically determining the sense of a word in a particular context. It has been observed that such approaches often find it difficult to beat the WordNet First Sense (WFS) baseline which assigns the sense irrespective of context. In this paper, we present our work on creating the WFS baseline for Hindi language by manually ranking the synsets of Hindi WordNet. A ranking tool is developed where human experts can see the frequency of the word senses in the sense-tagged corpora and have been asked to rank the senses of a word by using this information and also his/her intuition. The accuracy of WFS baseline is tested on several standard datasets. F-score is found to be 60%, 65% and 55% on Health, Tourism and News datasets respectively. The created rankings can also be used in other NLP applicati...

In this paper, the "Weighted Overlapping" Disambiguation method is presented and evaluated. This method extends the Lesk's approach to disambiguate a specific word appearing in a context (usually a sentence). Sense's definitions of the specific word, "Synset" definitions, the "Hypernymy" relation, and definitions of the context features (words in the same sentence) are retrieved from the WordNet database and used as an input of our Disambiguation algorithm. More precisely, for each sense of the word a sense bag is formed using the WordNet definition and the definitions of all the "Hypernyms" associated with the nouns and verbs in the sense's definition. A similar technique is used, for all the context words and the definitions of the "Hypernyms" (associated with the context nouns and verbs), to form a context bag. Then, a technique of assigning weights to words is applied. The weight for every word is inversely proportional to the hierarchy depth in the WordNet taxonomy of the associated "synset". Eventually, the disambiguation of a word in a context is based on the calculation of the similarity between the words of the sense bags and the context bag. The proposed method is evaluated in disambiguating all the nouns for all the sentences in the Brown files.

Word Sense Disambiguation (WSD) is the process of determining the exact sense of a particular word in accordance to the context in a computational manner. Such task plays an essential role in multiple fields of study such as Information Retrieval and Information Extraction. With the complexity of human language, WSD came up to solve the problem behind the ambiguity between senses in which a single word would yield different meaning. In this vein, determining the exact meaning of the certain word would facilitate the process of identifying the category of such text, accurate corresponding search results and providing an accurately summarized portion. Several approaches have been proposed for the WSD including statistical, semantic and machine learning techniques. This paper aims to provide a review of such approaches by tackling and categorizing the related works in accordance to the main types. 

In the work reported here, we present three important related issues. 1. We present an effective method of construction of the Marathi WordNet (http://www.cfilt.iitb.ac.in/wordnet/web mwn/) using the Hindi WordNet (http://www.cfilt.iitb.ac.in/wordnet/web hwn/), both of which are being developed at IIT Bombay. Henceforth we will refer to them as MWN and HWN respectively. 2. The Synset identity is the key to connect WordNets. 3. We present an interface to browse linked Hindi and Marathi WordNets (Bilingual WordNet) simultaneously for a given word either in Hindi or in Marathi. As an application, we present Word Sense Disambiguation (WSD) of nouns in Hindi. The system has been evaluated on the Corpora provided by Central Institute of Indian Languages (http://www.ciil.org/) and the results are encouraging.

Sentiment analysis has been performed in different languages and in various domains, such as movie reviews, product reviews and tourism reviews. However, not much work has been done in the area of books considering the high availability of book reviews on Hindi blogs and online forums. In this paper, a scorebased sentiment mining system for Hindi language is discussed, which captures the sentiment behind the words of book review sentences. We conducted three experiments using scores from the Hindi-SentiWordNet (H-SWN), first using parts-of-speech tags of opinion words to extract their potential scores. Then, we focused on word-sense disambiguation (WSD) to increase the accuracy of system. Finally, the classification results were improved by handling morphological variations. The results were validated against human annotations achieving an overall accuracy of 86.3%. The work was extended further using Hindi Subjective Lexicon (HSL). We also developed an annotated corpus of book reviews in Hindi.

Word Sense Disambiguation (WSD) – a challenge of Natural Language Processing, for Gujarati language. All natural languages have words that mean different thing in different contexts. Human beings are generally good at sensing those ambiguities but it is difficult for computers to understand that. But computers can sense that by following certain algorithms and rules. Four methodologies were discussed in this paper for implementing word sense disambiguation: AI-based method, Knowledge-based method, supervised method and unsupervised method. Seeming that knowledge based method is more accurate, the algorithms that are of knowledge based method, are used for further processing. It includes the standard Lesk algorithm, the simplified lesk algorithm, the lesk algorithm with synonyms and a baseline algorithm. With the comparison of these algorithms it is finally decided to use simplified lesk algorithm and it will be implemented on Java. Index Terms— Word Sense Disambiguation, Knowledge-based method, the Lesk Algorithm, the Simplified lesk algorithm

Current state-of-the-art Word Sense Disambiguation (WSD) algorithms are mostly supervised and use the P (Sense|W ord) statistic for annotation. This P (Sense|W ord) statistic is obtained after training the model on an annotated corpus. The performance of WSD algorithms do not match the efficiency and quality of human annotation. It is therefore important to know the role of the contextual clues in WSD. Human beings in turn, actuate the task of disambiguating the sense of a word, by gathering hints from the context words in the neighbourhood of the word. Contextual clues thus form the basic building block for the human sense disambiguation task. The need was thus felt for a tool, which could help us get a deeper insight into the human mind, while disambiguating polysemous words. As mentioned earlier, in the human mind, sense disambiguation highly depends on finding clues in corpus text, which finally lead to a winner sense. In order to make WSD algorithms more efficient, it is highly desirable to assimilate knowledge regarding contextual clues of words. In order to make WSD algorithms more efficient, it is highly desirable to assimilate knowledge regarding contextual clues of words, which aid in finding correct senses of words in that context. Hence, we developed a tool which could help a lexicographer mark the clues for disambiguating a word in a context. In the current phase, this tool lets the lexicographer select the clues from the gloss and example fields in the synset, and adds them to a database.

This paper presents a new model of WordNet that is used to disambiguate the correct sense of polysemy word based on the clue words. The related words for each sense of a polysemy word as well as single sense word are referred to as the clue words. The conventional WordNet organizes nouns, verbs, adjectives and adverbs together into sets of synonyms called synsets each expressing a different concept. In contrast to the structure of WordNet, we developed a new model of WordNet that organizes the different senses of polysemy words as well as the single sense words based on the clue words. These clue words for each sense of a polysemy word as well as for single sense word are used to disambiguate the correct meaning of the polysemy word in the given context using knowledge based Word Sense Disambiguation (WSD) algorithms. The clue word can be a noun, verb, adjective or adverb.
KEYWORDS
Word Sense Disambiguation, WordNet, Polysemy Words, Synset, Hypernymy, Context word, Clue Words

Besides synsets and semantic relations, synset glosses are an important feature of wordnets. However, due to the required effort, their creation is sometimes left undone. This happens in Onto.PT, a Portuguese wordnet created automatically, which does not have glosses. In our work, we exploited Portuguese dictionaries to automatically assign definitions to the synsets of Onto.PT. For this purpose, definitions are selected according to their overlap with the context of the synsets. Using three Portuguese dictionaries, more than one third of the Onto.PT synsets have at least one definition, with assignment accuracy close to 80%, which we believe to be interesting results.

Speaking and writing effectively is probably more important today than never before. Yet while the importance of communication skills increases, many people find it difficult to set about acquiring them. Dictionaries and thesauruses provide a great deal of information and self help material, but their greatest contribution must be restricted to meaning and spelling. With the increasing ambiguity in natural languages, the pressing need is a system that identifies and augments the correct sense to what a word means in a context of usage. Word Sense Disambiguation (WSD) is aimed to achieve the above said goal. There are numerous algorithms in order to disambiguate a word using WSD system such as Lesks’ algorithm, Walkers’ algorithm and Random Walk algorithm. In this paper a complete investigation of lesk algorithm is portrayed. It also includes a detailed analysis of the factors that need to be considered which affect the algorithm. While disambiguating any word in the context of the sentence the inclusive and exclusive of the words is very important and thus we show the grammatical words that creates problem and provide a list of such words that needs to be excluded while evaluating the lesk algorithm.

Word sense disambiguation (WSD) is a process of identifying proper meaning of words that may have multiple meanings. It is regarded as one of the most challenging problems in the field of natural language processing (NLP). Nepali Language also has words that have multiple meanings, thus giving rise to the problem of WSD in it. In this paper, we investigate the impact of NLP resources like morphology analyzer (MA) and machine readable dictionary (MRD) in ambiguity resolution. Our results show that the accuracy in WSD is better with the availability of NLP resources like morph analyzer, MRD etc. Lesk algorithm has been used to solve WSD problem using a sample Nepali WordNet containing few sets of Nepali nouns and the system is able to disambiguate these nouns only. The system was tested on a small set of data with limited number of nouns. The accuracy reading was between 50% - 70% depending on the sample data provided. When the same data was tested through manual morph analysis, the accuracy was seen to be considerably high (80%).

Word sense disambiguation (WSD) is a process of identifying proper meaning of words that may have multiple meanings. It is regarded as one of the most challenging problems in the field of natural language processing (NLP). Nepali Language also has words that have multiple meanings, thus giving rise to the problem of WSD in it. In this paper, we investigate the impact of NLP resources like morphology analyzer (MA) and machine readable dictionary (MRD) in ambiguity resolution. Our results show that the accuracy in WSD is better with the availability of NLP resources like morph analyzer, MRD etc. Lesk algorithm has been used to solve WSD problem using a sample Nepali WordNet containing few sets of Nepali nouns and the system is able to disambiguate these nouns only. The system was tested on a small set of data with limited number of nouns. The accuracy reading was between 50% - 70% depending on the sample data provided. When the same data was tested through manual morph analysis, the accuracy was seen to be considerably high (80%).

In this paper, the "Weighted Overlapping" Disambiguation method is presented and evaluated. This method extends the Lesk's approach to disambiguate a specific word appearing in a context (usually a sentence). Sense's definitions of the specific word, "Synset" definitions, the "Hypernymy" relation, and definitions of the context features (words in the same sentence) are retrieved from the WordNet database and used as an input of our Disambiguation algorithm. More precisely, for each sense of the word a sense bag is formed using the WordNet definition and the definitions of all the "Hypernyms" associated with the nouns and verbs in the sense's definition. A similar technique is used, for all the context words and the definitions of the "Hypernyms" (associated with the context nouns and verbs), to form a context bag. Then, a technique of assigning weights to words is applied. The weight for every word is inversely proportional to the hierarchy depth in the WordNet taxonomy of the associated "synset". Eventually, the disambiguation of a word in a context is based on the calculation of the similarity between the words of the sense bags and the context bag. The proposed method is evaluated in disambiguating all the nouns for all the sentences in the Brown files.

Abstract We suggest the method that permits building a set of candidates to be considered semantic primitives from the standard explanatory dictionary. Our method is based on the frequencies of the words that are reachable in a semantic network constructed from the dictionary. The method implements word sense disambiguation techniques, network construction, and reachability analysis. In part of word sense disambiguation we use an improved Lesk's algorithm.

Word sense disambiguation (WSD) is a process of identifying proper meaning of words that may have multiple meanings. It is regarded as one of the most challenging problems in the field of natural language processing (NLP). Nepali Language also has words that have multiple meanings, thus giving rise to the problem of WSD in it. In this paper, we investigate the impact of NLP resources like morphology analyzer (MA) and machine readable dictionary (MRD) in ambiguity resolution. Our results show that the accuracy in WSD is better with the availability of NLP resources like morph analyzer, MRD etc. Lesk algorithm has been used to solve WSD problem using a sample Nepali WordNet containing few sets of Nepali nouns and the system is able to disambiguate these nouns only. The system was tested on a small set of data with limited number of nouns. The accuracy reading was between 50% - 70% depending on the sample data provided. When the same data was tested through manual morph analysis, the accuracy was seen to be considerably high (80%).

Word Sense Disambiguation (WSD) is a task of identifying correct sense of a given word especially when it has multiple meanings. WSD acts as a foundation to many AI applications such as Data Mining, Information Retrieval and Machine Translation. It has drawn much interest in the last decade and much improved results are being obtained. For WSD we require a knowledge-base, using which we can resolve the ambiguity and identify the correct sense of a given word in a sentence. The most commonly used computational lexicon for WSD, especially for English, is the English Wordnet, which later inspired the use of Wordnet specifically for WSD for Indo-Aryan languages such as Hindi, Sanskrit, etc. In this paper we explore some ideas that may enhance the efficiency of knowledge-based contextual overlap WSD algorithms when they are used on Wordnets.

I always admired my adviser, Prof. Rajeev Sangal, whose ideals had a big influence on me which changed the way I perceived this world. I am one of those fortunate students to scribe my name in his students list. Without his support, I could not imagine myself starting a research career. His belief, "anyone can pursue research and create wonders" motivated me to contribute and made me feel to be a part of the research community. His generosity gave the freedom to enjoy all the privileges what not. I remain indebted to him all my life and just a mere thank you is not sufficient. My existence in this world would not have been possible without my family support. I am in this position because of their love and sacrifices. I love you all. My friend and partner of my research, Abhilash Inumella, motivated me to be strong and bold. The discussions we had, his unanswerable questions made my life tougher and helped me to bring out the best. Every word of my thesis has his contribution and this thesis can be claimed as his as well. He is the main reason to continue my research and also to apply for PhD. "Teach a man to fish; feed him for a lifetime". This is what he does for many of us. Abhilash, you are truly inspiring. My research life is incomplete without mentioning the people, Dr. Adam Kilgarriff and Dr. Diana McCarthy, who made me realize the best in me and also taught me research is fun. They showed me to the research world and laid a floral path to my future. Adam and Diana, you are the best and I adore you a lot. I would also like to thank Dr. Mark Stevenson who worked in collaboration with me and played a major role in getting me a PhD. The one who insisted me on completing the thesis and move on with my future goals helped me to realize the importance of many things in my life. Spandana, you are incredible. 5 I would like to acknowledge my friends and colleagues Ambati, Avinesh, Charan,