DOCSLIB.ORG

Indowordnet and Its Linking with Ontology

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Indowordnet and Its Linking with Ontology IndoWordNet and its Linking with Ontology Brijesh Bhatt Pushpak Bhattacharyya Center For Indian Language Technology, Center For Indian Language Technology, Department of Computer Science and Engineering, Department of Computer Science and Engineering, Indian Institute of Technology, Mumbai Indian Institute of Technology, Mumbai [email protected] [email protected] Abstract hierarchical structure of concepts related by sub- sumption relation, which can be shared between Reasoning about natural language requires applications. Though WordNet is often considered combining semantically rich lexical re- as an ontology (the synset corresponds to concept sources with world knowledge, provided and ‘hypernymy-hyponymy’ relation is similar to by ontologies. In this paper, we describe subsumption), it is a language specific resource linking of WordNets of Indian languages which may vary from language to language. The with an upper ontology SUMO (Sug- ontological issues in WordNet discussed in (pease gested Upper Merged Ontology). This and Fellbaum, 2010; Gangemi et al., 2003; Niles creates multilingual resource for Indian and Pease, 2003) are as follows, languages which can be used in various natural language processing applications. This paper presents the architecture of 1. Confusion between concept and individual: IndoWordNet- Linking of WordNets of WordNet synsets do not distinguish between seventeen different Indian languages and concept and individual. For example, both provides a method to link it with upper on- ‘Martial Art’ and ‘Karate’ are considered as tology SUMO. Two different systems: In- concept. doWordNet navigator and SIGMAKEE in- terface for Indian languages are developed 2. Confusion between object level and meta to access this resource. level concept: WordNet covers both object level and meta level concepts as hyponymy 1 Introduction of same concept. For example, concept ‘Ab- WordNet (Fellbaum, 1998) has emerged as a great straction’ includes both object level concept resource for the Natural Language Processing ap- ‘Time’ and meta level concept ‘Attribute’. plications. Following English WordNet, Word- Nets are built for many languages of the world. 3. Heterogeneous level of generality: Two hy- Hindi WordNet (D. Narayan and Bhattacharyya, ponyms of a concept may represent different 2002) is the first WordNet built for an Indian lan- level of generality. For example, as a hy- guage. WordNets for other 16 Indian languages ponymy of concept ‘Animal’, there is a gen- are being built from Hindi WordNet using expan- eral concept ‘chordate’ and a more specific sion approach (Vossen, 1998). Linking of all these concept ‘Work Animal’. WordNets provides rich knowledge base for the Indian languages, which can be useful for infor- 4. Lexical gap: A language may not have an in- mation extraction, retrieval and many other natural digenous lexeme to describe a concept. For language processing applications. example, vehicles can be divided into two classes, 1) Vehicles that run on the road and 1.1 WordNet and ontology 2) Vehicles that run on the rail, but English Ontology is defined as “Explicit specification of language does not have specific words to de- conceptualization”(Gruber, 1993). Ontology is a scribe these classes. “Proceedings of ICON-2011: 9th International Conference on Natural Language Processing, Macmillan Publishers, India. Also accessible from http://ltrc.iiit.ac.in/proceedings/ICON-2011” 1.2 Benefits of linking WordNet with and (17) Urdu. Together these languages repre- ontology sents three language families: Indo-Aryan, Dra- By keeping ontological relations in the formal on- vidian and Tibeto-Barman. The comparative study tology and linguistic relations in the lexicon, one of IndoWordNet with EuroWorNet is presented in can avoid merging two different levels of analy- (Bhattacharyya, 2010) sis and can capture the information needed about 2.1 Synset Categorization formal concepts and linguistic tokens (pease and Fellbaum, 2010). Linking of WordNet with on- Synsets of the Hindi WordNet are used as basis tology allows the language independent semantic to create synsets of WordNets of other languages. relations of ontology to be used for inferencing on As a synset is represented by a gloss and a set language specific words. The benefits of linking of words of a particular language, in many cases, ontology and WordNet are as follows (Niles and the synset representation of a concept may vary Pease, 2003): in sense across the languages. Also there exist some concepts for which there may not be words 1. The formal specifications of the ontology can in all the languages. For example, Kashmiri lan- be used with the WordNet in the sense that guage does not have words for the concepts like the axioms corresponding to the words can g}h (‘graaha’, Planet), som (‘som’), m\gl (‘man- be retrieved from the ontology. gal’). Kinship terms also vary across Indian lan- guages. To handle this concept divergence across 2. The formal axioms of ontology can be used languages, synsets are divided into different cate- with natural language text. gories. Table 1 describes these categories. Such classification of synsets helps in linking 3. Linking ontology concepts with WordNet can concepts of different languages. For example, if be used to check completeness of ontology. a synset belongs to the universal synset then it is 4. Concepts of different languages can be com- present in both Hindi and English. And if a synset pared and linked using ontology. belongs to the Pan-Indian category then it belongs to both Hindi and Gujarati. Thus, WordNet devel- 5. WordNet concepts can be refined and restruc- opment using expansion approach will be faster by tured using ontology. this method. This classification also helps in cross lingual information access. By identifying the cat- 6. Different domain ontologies can be linked us- egory of a synset, its presence in another language ing WordNet concepts. can be easily predicted. Till date, 7163 universal synsets and 1356 Pan- 1.3 Organization of the paper Indian synsets have been identified and are now The remaining of the paper is organized as fol- linked across all languages. Language specific lows: Section 2 describes the IndoWordNet. The synsets are being developed and later they will be selection criteria for upper ontology and a compar- linked by translating them into Hindi and English. ative study of upper ontology is given in Section 3 and 4. Section 5 describes the method to link In- 3 Survey of upper ontology doWordNet with ontology and interfaces designed Ontologies are categorized into three different to access the system. Observations and conclu- types according to their level of generality (Guar- sions are discussed in section 6 and 7 respectively. ino, 1998). Top level/Upper ontology, Domain 2 IndoWordNet specific ontology and application specific ontol- ogy. Upper ontology defines very general con- Seeing the enormous potential of WordNet, 17 cepts independent of application or domain. Up- out of 22 official languages of India have started per ontologies are useful in linking and devel- developing WordNets. These languages are: (1) opment of more specific domain/application on- Hindi (2) Marathi (3) Konkani (4) Sanskrit (5) tology. There are various upper ontologies like Nepali (6) Kashimiri (7) Assamese (8) Tamil (9) SUMO, DOLCE, CYC etc. The ontological Malyalam (10) Telugu (11) Kannad (12) Manipuri choices for designing upper ontologies, discussed (13) Bodo (14) Bangla (15) Punjabi (16) Gujarati in (Oberle et al., 2007), are as follows, Table 2: Comparison of Upper ontologies Case SUMO DOLCE Open CYC License Open Open Free Table 1: Synset categories in IndoWordNet subset Category Description of Cyc Universal These concepts appear in all the Modularity Yes No Yes Language KIF, OWL Cyc languages. These concepts are es- OWL sential and most frequently used. Multiplicative(M)- -MM For example, s y (‘soorya’, sun) Reductionist(R) Descriptive(D)- DDD Pan-Indian Concepts common to Indian lan- prescriptive(Pr) guages and linkable across all In- Endurant(E)- No Yes Yes dian languages but does not have Perdurant(Pd) parallel concepts in English. For Universal(U)- Both Pt Both Particular(Pt) example, tblA (‘tabalaa’, An In- Linking to Word- Full Partial Partial dian rhythm instrument) Net In-Family These concepts are common in specific subset of Indian lan- 1. Endurant-Perdurant : An endurant is an en- guages and linkable across all lan- tity which exists in full in every instant at guages of the family. For example, which it exists at all. A perdurant “unfolds cAcA (‘chacha’ ,paternal uncle), itself over time in successive temporal parts BEtjA (‘bhatija’, brother’s son) or phases.” Both endurants and perdurants are taken to be concrete particulars, i.e., in- Language These are the concepts specific to stances. Specific a culture or a language. These may include local food, festivals, 2. Descriptive-prescriptive :A descriptive on- etc. For example, Ebh (‘bihu’ , tology tries to capture more commonsense Name of a festival celebrated in and social notions based on natural language Assam state of India) word is very usage and human cognition. Concepts are specific to the state and culture and divided into things and events. A prescrip- does not appear in any other lan- tive ontology emphasizes upon the scientific guage. and philosophical perspectives. All the con- structs in revisionary ontology are space-time Rare This includes very specific con- objects. cepts adopted in most of the lan- multiplicative-reductionist multiplicative guages. Specific scientific terms 3. : In like ‘ngram’ belongs to this cate- upper ontology concepts can include any- gory thing that reality seems to require. Contrar- ily, reductionist ontology reduces the number Synthesized Synset created in a language due of concepts to the fewest primitives sufficient to influence of another language. to derive the rest of the complex reality. These synsets are not natural to 4. Universal-particular : Universals are the en- the language but required to link tities that have instances, while particulars WordNets of two different lan- are entities that do not have instances.
Load more

Recommended publications
  • An Efficient Database Design for Indowordnet Development Using
    An Efficient Database Design for IndoWordNet Development Using Hybrid Approach Venkatesh Prabhu2 Shilpa Desai1 Hanumant Redkar1 N eha Prabhugaonkar1 Apurva N agvenkar1 Ramdas Karmali1 (1) GOA UNIVERSITY, Taleigao - Goa (2) THYWAY CREATIONS, Mapusa - Goa [email protected], [email protected], [email protected], [email protected], [email protected], [email protected] ABSTRACT WordNet is a crucial resource that aids in Natural Language Processing (NLP) tasks such as Machine Translation, Information Retrieval, Word Sense Disambiguation, Multi-lingual Dictionary creation, etc. The IndoWordNet is a multilingual WordNet which links WordNets of different Indian languages on a common identification number given to each concept. WordNet is designed to capture the vocabulary of a language and can be considered as a dictionary cum thesaurus and much more. WordNets for some Indian Languages are being developed using expansion approach. In this paper we have discussed the details and our experiences during the evolution of this database design while working on the Indradhanush WordNet Project. The Indradhanush WordNet Project is working on the development of WordNets for seven Indian languages. Our database design gives an efficient plan for storage of WordNet data for all languages. In addition it extends the design to hold specific concepts for a language. KEYWORDS: WordNet, IndoWordNet, synset, database design, expansion approach, semantic relation, lexical relation. Proceedings of the 3rd Workshop on South and Southeast Asian Natural Language Processing (SANLP), pages 229–236, COLING 2012, Mumbai, December 2012. 229 1 Introduction 1.1 WordNet and its storage methods WordNet (Miller, 1993) maintains the concepts in a language, relations between concepts and their ontological details.
    [Show full text]
  • Exploring Resources in Word Sense Disambiguation for Marathi Language Amit Patil1, Chhaya Patil2, Dr
    www.rspsciencehub.com Volume 02 Issue 10S October 2020 Special Issue of First International Conference on Advancements in Management, Engineering and Technology (ICAMET 2020) Exploring Resources in Word Sense Disambiguation for Marathi Language Amit Patil1, Chhaya Patil2, Dr. Rakesh Ramteke3, Dr. R. P. Bhavsar4, Dr. Hemant Darbari5 1,2 Assistant Professor, Department of Computer Application, RCPET’s IMRD, Maharashtra, India 3,4Professor, School of Computer Sciences, KBC North Maharashtra University, Maharashtra, India 5Director General, Centre for Development of Advanced Computing (C-DAC), Maharashtra, India Abstract Word Sense Disambiguation (WSD) is one of the most challenging problems in the research area of natural language processing. To find the correct sense of the word in a particular context is called Word Sense Disambiguation. As a human, we can get a correct sense of the word given in the sentence because of word knowledge of that particular natural language, but it is not an easy task for the machine to disambiguate the word. Developing any WSD system, it required sense repository and sense dictionary. It is very costly and time-consuming to build these resources. Many foreign languages have available these resources, that is why most of the foreign languages like English, German, Spanish etc lot of work is done in these Natural languages. When we look for Indian languages like Hindi, Marathi, Bengali etc. very less work is done. The reason behind this is resource-scarcity. In this paper, we majorly focus on Marathi Language Word Sense Disambiguation because of very less work is done in the Marathi Language as compared to Hindi and other Indian Languages.
    [Show full text]
  • WWDS Apis: Application Programming Interfaces for Efficient Manipulation of World Wordnet Database Structure
    Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) WWDS APIs: Application Programming Interfaces for Efficient Manipulation of World WordNet Database Structure Hanumant Redkar1, Sudha Bhingardive1, Kevin Patel1, Pushpak Bhattacharyya1 Neha Prabhugaonkar2, Apurva Nagvenkar2, Ramdas Karmali2 1Indian Institute of Technology Bombay, Mumbai, India 2Goa University, Goa, India {hanumantredkar, bhingardivesudha, kevin.svnit, pushpakbh}@gmail.com {nehapgaonkar.1920, apurv.nagvenkar, ramdas.karmali}@gmail.com Abstract example, developers can potentially extract information WordNets are useful resources for natural language from other WordNets through WWDS and its APIs that is processing. Various WordNets for different languages have missing in their source WordNet. The WWDS and WWDS been developed by different groups. Recently, World APIs are explained in the following sections. WordNet Database Structure (WWDS) was proposed by Redkar et. al (2015) as a common platformm to store these different WordNets. However, it is underutilized due to lack World WordNet Database Structure of programming interface. In this paper, we present WWDS APIs, which are designed to address this shortcoming. These WWDS is an efficient storage mechanism which uses WWDS APIs, in conjunction with WWDS, act as a wrapper that enables developers to utilize WordNets without multiple databases to accommodate different WordNets. Its worrying about the underlying storage structure. The APIs design is based on IndoWordNet database structure are developed in PHP, Java, and Python, as they are the (Prabhu et al., 2012). The language independent preferred programming languages of most developers and information such as semantic relations, ontology details, researchers working in language technologies. These APIs etc. is stored in a single master database named can help in various applications like machine translation, word sense disambiguation, multilingual information wordnet_master.
    [Show full text]
  • Comparative Study on Currently Available Wordnets
    International Journal of Applied Engineering Research ISSN 0973-4562 Volume 13, Number 10 (2018) pp. 8140-8145 © Research India Publications. http://www.ripublication.com Comparative Study on Currently Available WordNets Sreedhi Deleep Kumar Reshma E U PG Scholar PG Scholar Department of Computer Science and Engineering Department of Computer Science and Engineering Vidya Academy of Science and Technology Vidya Academy of Science and Technology Thrissur, India. Thrissur, India. Sunitha C Amal Ganesh Associate Professor Assistant Professor Department of Computer Science and Engineering Department of Computer Science and Engineering Vidya Academy of Science and Technology Vidya Academy of Science and Technology Thrissur, India. Thrissur, India. Abstract SinoTibetan, Tibeto-Burman and Austro-Asiatic. The major ones are the Indo-Aryan, spoken by the northern to western WordNet is an information base which is arranged part of India and Dravidian, spoken by southern part of India. hierarchically in any language. Usually, WordNet is The Eighth Schedule of the Indian Constitution lists 22 implemented using indexed file system. Good WordNets languages, which have been referred to as scheduled available in many languages. However, Malayalam is not languages and given recognition, status and official having an efficient WordNet. WordNet differs from the encouragement. dictionaries in their organization. WordNet does not give pronunciation, derivation morphology, etymology, usage notes, A Dictionary can be called as are source dealing with the or pictorial illustrations. WordNet depicts the semantic relation individual words of a language along with its orthography, between word senses more transparently and elegantly. In this pronunciation, usage, synonyms, derivation, history, work, a general comparison of currently browsable WordNets etymology, etc.
    [Show full text]
  • Improving Semantic Similarity with Cross-Lingual Resources: a Study in Bangla—A Low Resourced Language
    informatics Article Improving Semantic Similarity with Cross-Lingual Resources: A Study in Bangla—A Low Resourced Language Rajat Pandit 1,* , Saptarshi Sengupta 2, Sudip Kumar Naskar 3, Niladri Sekhar Dash 4 and Mohini Mohan Sardar 5 1 Department of Computer Science, West Bengal State University, Kolkata 700126, India 2 Department of Computer Science, University of Minnesota Duluth, Duluth, MN 55812, USA; [email protected] 3 Department of Computer Science & Engineering , Jadavpur University, Kolkata 700032, India; [email protected] 4 Linguistic Research Unit, Indian Statistical Institute, Kolkata 700108, India; [email protected] 5 Department of Bengali, West Bengal State University, Kolkata 700126, India; [email protected] * Correspondence: [email protected] Received: 17 February 2019; Accepted: 20 April 2019; Published: 5 May 2019 Abstract: Semantic similarity is a long-standing problem in natural language processing (NLP). It is a topic of great interest as its understanding can provide a look into how human beings comprehend meaning and make associations between words. However, when this problem is looked at from the viewpoint of machine understanding, particularly for under resourced languages, it poses a different problem altogether. In this paper, semantic similarity is explored in Bangla, a less resourced language. For ameliorating the situation in such languages, the most rudimentary method (path-based) and the latest state-of-the-art method (Word2Vec) for semantic similarity calculation were augmented using cross-lingual resources in English and the results obtained are truly astonishing. In the presented paper, two semantic similarity approaches have been explored in Bangla, namely the path-based and distributional model and their cross-lingual counterparts were synthesized in light of the English WordNet and Corpora.
    [Show full text]
  • A Sentiment Analysis of Gujarati Text Using Gujarati Senti Word Net
    International Journal of Innovative Technology and Exploring Engineering (IJITEE) ISSN: 2278-3075, Volume-8 Issue-9, July 2019 A Sentiment Analysis of Gujarati Text using Gujarati Senti word Net Lata Gohil, Dharmendra Patel Abstract: Sentiment Analysis plays vital role in decision II. RELATED WORK making. For English language intensive research work is done in this area. Very less work is reported in this domain for Indian Sentiment analysis is useful method to understand opinion languages compared to English language. Gujarati language is expressed in text. “It is one of the most active research areas almost unexplored for this task. More data in form of movie in natural language processing and is also widely studied in reviews, product reviews, social media posts etc are available in data mining, web mining, and information retrieval” [7]. regional languages as people like to use their native language on Beginning research work on sentiment analysis was mostly Internet which leads to need of mining these data in order to understand their opinion. Various tools and resources are focused on English language. However increasing developed for English language and few for Indian languages. non-English language content on Internet led demand to work Gujarati is resource poor language for this task. Motive of this towards other languages. There are two approaches namely paper is to develop sentiment lexical resource for Gujarati Lexicon and Machine Learning are widely explored for language which can be used for sentiment analysis of Gujarati sentiment analysis. Large amount of annotated data is the key text. Hindi SentiWordNet (H-SWN) [1] and synonym relations of requirement of Machine learning approach.
    [Show full text]
  • S.ARULMOZI Assistant Professor Mobile: +91-9441330510 Dept
    S.ARULMOZI Assistant Professor Mobile: +91-9441330510 Dept. of Dravidian & Computational Linguistics Residence: +91-8570-278214 Dravidian University, Kuppam 517426, India Email: [email protected] EDUCATION Ph.D., Applied Linguistics, University of Hyderabad, 1999. PGDTS, Translation Studies, University of Hyderabad, 1995 (66%) M.Phil., Applied Linguistics, University of Hyderabad, 1992 (70.8%) M.A., Linguistics, Bharathiar University, 1990 (64.4%) B.Sc., Chemistry, Bharathiar University, 1988. (54.6%) H.Sc., Board of Higher Secondary Education, Tamil Nadu, 1985 (61.75%) S.S.L.C., Board of Secondary Education, Tamil Nadu, 1983 (64.5%) EMPLOYMENT Designation Department University/Institution Period Assistant Professor Department of Dravidian Dravidian University 29 Dec 2005 and Computational onwards Linguistics Guest Faculty Centre for ALTS University of Hyderabad 19 Jan 2005 to 28 Dec 2005 Member Research AU-KBC Research Centre Anna University 29 Dec 2000 to Staff 15 Jan 2005 Project Fellow Department of Linguistics Tamil University 21 Jan 1999 to 2 Jul 2000 Language Assistant- DoE Project Central Institute of Indian 8 Jun 1998 to Tamil Languages 31 Oct 1998 RESEARCH EXPERIENCE Course Topic Research Guide Year University Ph.D. Aspects of Inflectional Prof. Probal Dasgupta 1998 University of Morphophonology: A & Dr. N. Krupanandam Hyderabad Computational Approach M.Phil. Dynamics of Translation in Prof. Probal Dasgupta 1992 University of Reconstructing Sci-Tech Hyderabad Terminologies M.A. Advertisement Headlines Prof. C.Shanmugom 1990 Bharathiar University 1 ACADEMIC OUTREACH S.No. Role Topic Event Place Date 1. Resource Person BIS Tagset for Workshop on Tamil Madurai 03-03-2013 Tamil POS POS Tagging Kamaraj Tagging University 2.
    [Show full text]
  • An Online Interface for Synset Creation with Special Reference to Sanskrit
    Introduction to Synskarta: An Online Interface for Synset Creation with Special Reference to Sanskrit Hanumant Redkar, Jai Paranjape, Nilesh Joshi, Irawati Kulkarni, Malhar Kulkarni, Pushpak Bhattacharyya Center for Indian Language Technology, Indian Institute of Technology Bombay, India. [email protected], [email protected], [email protected], [email protected], [email protected], [email protected] In this paper, we have taken reference of San- Abstract skrit WordNet 3. Sanskrit is an Indo-Aryan lan- guage and is one of the ancient languages. It has WordNet is a large lexical resource express- vast literature and a rich tradition of creating ing distinct concepts in a language. Synset is léxica. The roots of all languages in the Indo Euro- a basic building block of the WordNet. In this pean family in India can be traced to Sanskrit paper, we introduce a web based lexicogra- (Kulkarni et al., 2010). Sanskrit WordNet is con- pher's interface ‘Synskarta’ which is devel- structed using expansion approach where Hindi oped to create synsets from source language to target language with special reference to WordNet is used as a source (Kulkarni et al., Sanskrit WordNet. We focus on introduction 2010). and implementation of Synskarta and how it While developing Sanskrit WordNet, lexicogra- can help to overcome the limitations of the phers create Sanskrit synsets by referring to Hindi existing system. Further, we highlight the fea- synsets and by following the three principles of tures, advantages, limitations and user evalua- synset creation (Bhattacharyya, 2010). Since San- tions of the same. Finally, we mention the skrit came into existence much before Hindi, it has scope and enhancements to the Synskarta and many words which are not present in Hindi its usefulness in the entire IndoWordNet WordNet.
    [Show full text]
  • Gujarati Language: Research Issues, Resources and Proposed Method on Word Sense Disambiguation
    International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Volume-8, Issue-2S11, September 2019 Gujarati Language: Research Issues, Resources and Proposed Method on Word Sense Disambiguation Tarjni Vyas, Amit Ganatra B. GUJARATI GRAMMAR Abstract: Gujarati Word Sense Disambiguation (WSD) is an There are 32 consonants and 8 vowels in Gujarati language. exceptionally complex when it comes to Natural language handling because it needs to manage complexities found in a No Components Number Details language. In this paper, the discussion has put forward about 1 Consonants 32 Fig2 Guajarati language, Gujarati Wordnet and Gujarati word sense disambiguation. Accordingly, the deep learning approach is 2 Vowels 8 Fig2 found to perform better in Gujarati WSD yet one of its weakness is 3 Tenses 3 Past,Present, Future the prerequisite of enormous information sources without which 4 Vachans 2 Singular,Plural preparing is close to impossible. On the other hand, utilizes 5 Sentence Structure 3 Subject,object,Verb information sources to choose the meanings of words in a specific setting. Provided with that, deep learning approaches appear to be Sentence structure is made in the order of Subject, Object and more suitable to manage word sense disambiguation; however, the process will always be challenging given the ambiguity of Verb in Gujarati language. natural languages. There are three Tenses in Gujarati Past Tense, Present Tense Keywords: Word Sense Disambiguation, Gujarati Language, and Future Tense. There are two types of Vachans in Deep learning, Natural language processing, Lesk Gujarati.Singular and Plural. Gujarati Language includes Algorithm, Wordnet. following cases.(Table 1) I.
    [Show full text]
  • Adding a Sense-Annotated Telugu Lexicon
    Enrichment of OntoSenseNet: Adding a Sense-annotated Telugu lexicon Sreekavitha Parupalli and Navjyoti Singh Center for Exact Humanities (CEH) International Institute of Information Technology, Hyderabad, India [email protected] [email protected] Abstract The paper describes the enrichment of OntoSenseNet- a verb- centric lexical resource for Indian Languages. This resource contains a newly developed Telugu-Telugu dictionary. It is important because na- tive speakers can better annotate the senses when both the word and its meaning are in Telugu. Hence efforts are made to develop a soft copy of Telugu dictionary. Our resource also has manually annotated gold standard corpus consisting 8483 verbs, 253 adverbs and 1673 adjectives. Annotations are done by native speakers according to defined annotation guidelines. In this paper, we provide an overview of the annotation proce- dure and present the validation of our resource through inter-annotator agreement. Concepts of sense-class and sense-type are discussed. Addi- tionally, we discuss the potential of lexical sense-annotated corpora in improving word sense disambiguation (WSD) tasks. Telugu WordNet is crowd-sourced for annotation of individual words in synsets and is compared with the developed sense-annotated lexicon (OntoSenseNet) to examine the improvement. Also, we present a special categorization (spatio-temporal classification) of adjectives. 1 Introduction Lexically rich resources form the foundation of all natural language processing (NLP) tasks. Maintaining the quality of resources is thus a high priority issue [5]. Hence, it is important to enhance and maintain the lexical resources of any language. This is of significantly more importance in case of resource poor languages like Telugu [19].
    [Show full text]
  • Development of Assamese Wordnet
    Development of Assamese WordNet Iftikar Hussain, Navanath Saharia and Utpal Sharma Department of Computer Science & Engineering Tezpur University, Napaam, India-784028 [email protected], [email protected], [email protected] Abstract. An important challenge in the task of semantic analysis is the fact that in natural languages several words may denote the same concept, and a single word form may denote different concepts. WordNet is a repository of information about such characteristics of words, in a readily accessible format. A WordNet may be developed for a language for which computational processing is attempted. It calls for efforts in the domain of linguistics as well as computer science. In this paper we describe our works towards the development of WordNet for Assamese language, an official language of India. We cover proposed formats for the WordNet database text files and also an Application Programming Interface (API) of the Assamese WordNet. 1 Introduction One of the main challenges in Natural Language Processing (NLP) is determining the appropriate sense of each word that occurs in input expressions. Words in natural languages often have multiple senses, and often several distinct words denote the same sense. WordNet helps to overcome such challenges. WordNet is a database that consists of words or collocations. Words having similar senses are grouped together and the groups are interconnected through some lexical and semantic relations. Users or their applications can make queries on it and can find out appropriate senses of words distinctly. Assamese is one of the 22 official languages in India, spoken by nearly 30 million people.
    [Show full text]
  • Indowordnet Dictionary: an Online Multilingual Dictionary Using Indowordnet
    IndoWordNet Dictionary: An Online Multilingual Dictionary using IndoWordNet Hanumant Redkar Sandhya Singh Center for Indian Language Technology, Center for Indian Language Technology, Indian Institute of Technology Bombay, India Indian Institute of Technology Bombay, India [email protected] [email protected] Nilesh Joshi Anupam Ghosh Center for Indian Language Technology, Center for Indian Language Technology, Indian Institute of Technology Bombay, India Indian Institute of Technology Bombay, India [email protected] [email protected] Pushpak Bhattacharyya Department of Computer Science and Engineering, Indian Institute of Technology Bombay, India [email protected] based, thesaurus based, word usage based and Abstract language based. English WordNet infor- mation is also rendered using this interface. India is a country with diverse culture, lan- The IndoWordNet dictionary will help users guage and varied heritage. Due to this, it is to know meanings of a word in multiple Indi- very rich in languages and their dialects. Be- an languages. ing a multilingual society, a dictionary in multiple languages becomes its need and one of the major resources to support a language. 1 Introduction There are dictionaries for many Indian lan- guages, but very few are available in multiple Language is a constituent element of civilization. languages. WordNet is one of the most prom- In a country like India, diversity is its primary as- inent lexical resources in the field of Natural pect. This leads to varied languages and their dia- Language Processing. IndoWordNet is an in- lects. There are numerous languages in India which tegrated multilingual WordNet for Indian lan- belong to different language families. These lan- guages.
    [Show full text]