Aligning the IndoWordNet with the Princeton WordNet

In the work reported here, we present three important related issues.

2009

Words in any language are related to various other words in it. Some relations are lexical while some are semantic. WordNet [English WordNet] is an excellent tool that allows one to navigate through various relations a word has with others to get a holistic view of the meaning it conveys. The synsets convey the sense, antonyms give the words with opposite sense, meronymy and hyponymy help one in identifying the parts of the object and the objects of which the given word is a part of, hypernymy and hyponymy give an idea of ontological classification. In case of verbs the entailment relation helps in understanding the activity-subactivity relation.

While validating Malayalam wordNet we have found out that Many synsets are not linked to the core or Major wordNet. (Thanks to the Trento University which has found out this lacunae.) Especially many adjectives in Malayalam wordNet are not linked to the main wordNet. We are planning to explore the reason for the lacunae and trying to come out with a possible solution. According to the information sent by Nadu of Trento University, 2416 items declared as adjectives, 123 items marked as adverbs, 78 items marked as verbs and 139 items marked as nouns from Malayalam are not linked to the core wordNet.

The main objective of DWN is to develop an extensive and high quality multlingual database with wordnets for Dravidian languages in a cost-effective manner. The project will also develop a language independent set of semantic concepts linking the language networks together. The resources will be field tested for adequacy in an information retrieval application. The ultimate objectives are to move toward standardisation of semantic classification of information for all Dravidian languages and to provide resources for development of applications, which can operate in a selected language or over a range of languages. Dravidian WordNet will be a multilingual lexical database with wordnets for four major Dravidian languages, which will be structured along the same lines as the Princeton WordNet (Fellbaum 1998). WordNet will contain information about nouns, verbs, adjectives and adverbs and will be organized around the notion of a synset. A synset is a set of words with the same part-of-speech that can be interchanged in a certain context. For example, {car; auto; automobile; machine; motorcar} form a synset because they can be used to refer to the same concept. A synset is often further described by a gloss: "4-wheeled; usually propelled by an internal combustion engine". Finally, synsets can be related to each other by semantic relations, such as hyponymy (between specific and more general concepts), meronymy (between parts and wholes), cause, etc. In this example, taken from English WordNet, the synset {car; auto; automobile; machine; motorcar} is related to: • a more general concept or the hyperonym synset: {motor vehicle; automotive vehicle}, • more specific concepts or hyponym synsets: e.g. {cruiser; squad car; patrol car; police car; prowl car} and {cab; taxi; hack; taxicab}, • parts it is composed of: e.g. {bumper}; {car door}, {car mirror} and {car window}. Each of these synsets is again related to other synsets as is illustrated for {motor vehicle; automotive vehicle} that is related to {vehicle}, and {car door} that is related to other parts: {hinge; flexible joint}, {armrest}, {doorlock}. By means of these and other semantic/conceptual relations, all word meanings in a language can be interconnected, constituting a huge network or wordnet. Such a wordnet can be used for making semantic inferences (what things can be used as vehicles), for finding alternative expressions or wordings (what words can refer to vehicles), or for simply expanding words to sets of semantically related or close words, in e.g. information retrieval. Furthermore, semantic networks give information on the lexicalization patterns of languages, on the conceptual density of areas of the vocabulary and on the distribution of semantic distinctions or relations over different areas of the vocabulary. Each of the Dravidain wordnet will be a similar network of relations between word meanings in a specific language. The semantic relations are therefore considered as language-internal relations. In addition to the language-internal relations, each synset will be linked to the closest synset in TWN. By storing the wordnets in a central lexical database system we will create a multilingual database, where the synsets from TWN will function as an inter-lingual index. In this database it will be possible to go from one synset in a wordnet to a synset in another wordnet, which will be linked to the same TWN concept. Such a multilingual database will be useful for cross-language information retrieval, for transfer of information from one resource to another or for simply comparing the different wordnets. A comparison may tell us something about the consistency of the relations across wordnets, where differences may point to inconsistencies or to language-specific properties of the resources, or also to properties of the language itself. In this way, the database can also be seen as a powerful tool for studying lexical semantic resources and their language-specificity. In DWN, we initially will work on 4 languages: Tamil, Malayalam, Kannada and Telugu. This will be linked with Indo WordNet, a project going on in IIT, Bombay under the supervision of Dr. Pushpak Bhatacharya. The vocabulary will comprise all the generic and basic words of the languages: i.e. it includes all the meanings and concepts that are needed to relate more specific meanings, and all the words that occur most frequently in general corpora. For specific domains, sub-vocabulary will be added to illustrate the possibility of integrating terminology in such a general-purpose lexicon. On a longer term we expect that DWN will open up a whole range of new applications and services in India at a trans-national and trans-cultural level. It will give information on the typical lexicalization patterns across languages, which will be crucial for machine translation and language learning systems. It will give non-native users and non-skilled writers the possibility to navigate or browse through the vocabulary of a language in new ways, giving them an overview of expression which is not feasible in traditional alphabetically-organized resources. Finally, it will stimulate the development of sophisticated lexical knowledge bases that are crucial for a whole gamut of future applications, ranging from basic information retrieval to question/answering systems, language understanding and expert systems, from summarizers to automatic translation tools and resources.

2018

Introduction The WordNet is a lexical resource. It is lexicon based on psycholinguistics principles. It organizes the lexical information in terms of word meanings. It is a system for bringing together different lexical and semantic relations between words. The WordNet is being developed using the expansion approach with the help of tools provided by IIT Bombay. Malayalam wordNet is a part of Dravidian wordNet which in turn is a part of Indo wordNet. Malayalam WordNet is being built in Centre for Excellence in Computational Engineering and Network, Amrita Vishwa Vidyapeetham, Coimbatore, Tamil Nadu. In a language, a word may appear in more than one grammatical categories and within that grammatical category it can have multiple senses. These categories and all senses are captured in the WordNet. WordNet supports the grammatical categories namely Nouns, Verbs, Adjectives and Adverbs. All words which depict the same sense (same meaning) are grouped together to form a single entry in the WordNet. This forms synonym set or synset. Synsets are the basic building blocks of WordNet. For each word can there is a synonym set, or synset in the WordNet representing one lexical concept. This is done to remove ambiguity in cases where a single word has multiple meanings. 1. Relations in WordNet A WordNet is a word sense network. A word sense node in this network is a synset which is regarded as a basic object in the WordNet. Each synset in the WordNet is linked with other synsets through the well-known lexical and semantic relations of hypernymy, hyponymy, meronymy, troponymy, antonymy, entailment etc. Semantic relations are between synsets and lexical relations are between words. These relations serve to organize the lexical knowledge base. 2. Nouns in Wordnet Nouns are organized in a lexical inheritance system. A typical definition of a noun contains a superordinate term followed by certain distinguishing features. The relation of subordination (or class inclusion or subsumption), which is called hyponymy organizes nouns into a lexical hierarchy. The superordinate relation generates a hierarchical semantic organization of nouns. Synset which contains a group of synonyms representing a concept is the building blocks of noun wordNet. Synonymy is a lexical relation that holds between word forms, whereas the semantic relation holds between lexicalized concepts. The hierarchical structuring of nouns can be assumed to be contained in a single hierarchy. Instead, WordNet divides the nouns into several hierarchies, each with a different unique beginner. The semantic fields or domains (Lehrar 1974) which contain their own stock of vocabulary can be equated with these multiple hierarchies. Unique beginner corresponds roughly to a primitive semantic component in a compositional theory of lexical semantics. There is a list of 25 unique beginners for noun source files of EuroWordNet (Vossen 1998): {act, activity} {animal, fauna}{artifact}{attribute} {body} {cognition, knowledge}{communication}{event, happening}{feeling, emotion}{food}{group, grouping}{location}{motivation, motive}{natural object}{natural phenomenon}{person, human being} {plant, flora}{possession}{process}{quantity, amount}{relation}{shape}{state}{substance}{time}

Sanskrit has a rich source of lexical resources in the form of various kinds of dictionaries, and a thesaurus in the form of Amarakośa.

International Journal of Advanced Computer Science and Applications

The authors of this research paper present a mechanism for dealing with loanwords, missing words, and newly developed terms inclusion issues in WordNets. WordNet has evolved as one of the most prominent Natural Language Processing (NLP) toolkits. This mechanism can be used to improve the WordNet of any language. The authors chose to work with the Hindi and Gujarati languages in this research work to achieve a higher quality research aspect because these are the languages with major dialects. The research work used more than 5000 Hindi verse-based data corpus instead of a prose-based data corpus.As a result, nearly 14000 Hindi words were discovered that were not present in the popular Hindi IndoWordNet, accounting for 13.23 percent of the total existing word count of 105000+. Working with idioms was a distinct method for the Gujarati language. Around 3500 idioms data were used, and nearly 900 Gujarati terms were discovered that did not exist in the IndoWordNet, accounting for nearly 1.4 percent of the total of 64000+ Gujarati words in the IndoWordNet. It will also contribute almost 14000 Hindi words and around 900 Gujarati words to the IndoWordNet project.

Zenodo (CERN European Organization for Nuclear Research), 2008

Sanskrit has a rich source of lexical resources in the form of various kinds of dictionaries, and a thesaurus in the form of Amarakośa. Further the rich derivational morphology provides various kinds of relations between the derived words with their head words. With the advent of computational technology now it is possible to build tools that can help a serious reader of Sanskrit to navigate through various words passing through different linkages the word has, to get a holistic view of the meaning of a word, provided such a network exists. Present work is the first step in that direction. We have initiated the process of building a network of Sanskrit words with Amarakośa as the starting point. Since Sanskrit has rich inflectional morphology, we have also linked the web interface to Amarakośa with the inflectional morph-analyser. Further to provide various lexical and semantic relations between words, we explored the possibilities of using existing Hindi WordNet. It was found that the comparison of synsets of Hindi WordNet with that of Amarakośa is useful in improving the quality of Hindi WordNet on the one hand while enhancing the Sanskrit synsets quantitatively on the other hand.

Sanskrit has a rich source of lexical resources in the form of various kinds of dictionaries, and a thesaurus in the form of Amarakośa.

WordNet is an essential resource in Natural language processing. A lexical database like WordNet has a variety of practical applications like machine translation, information retrieval and many more. The creation of a comprehensive WordNet requires many hands and minds working collaboratively. In addition WordNet creation and maintenance demands creation of a wide range of software tools. All this is possible with help from some funding agency.