(Redirected from WordNet)
- AKA: English WordNet Database.
- See: Lexeme, George A. Miller.
- (Wikipedia, 2011) http://en.wikipedia.org/wiki/WordNet
- WordNet is a lexical database for the English language. It groups English words into sets of synonyms called synsets, provides short, general definitions, and records the various semantic relations between these synonym sets. The purpose is twofold: to produce a combination of dictionary and thesaurus that is more intuitively usable, and to support automatic text analysis and artificial intelligence applications. The database and software tools have been released under a BSD style license and can be downloaded and used freely. The database can also be browsed online. WordNet was created and is being maintained at the Cognitive Science Laboratory of Princeton University under the direction of psychology professor George A. Miller. Development began in 1985. Over the years, the project received funding from government agencies interested in machine translation. As of 2009, the WordNet team includes the following members of the Cognitive Science Laboratory: George Armitage Miller, Christiane Fellbaum, Randee Tengi, Pamela Wakefield, Helen Langone and Benjamin R. Haskell. WordNet has been supported by grants from the National Science Foundation, DARPA, the Disruptive Technology Office (formerly the Advanced Research and Development Activity), and REFLEX. George Miller and Christiane Fellbaum were awarded the 2006 Antonio Zampolli Prize for their work with WordNet.
- (Toral et al., 2008) ⇒ Antonio Toral, Rafael Muñoz, and Monica Monachini. (2008). “Named Entity WordNet.” In: Proceedings of the 6th Conference on Language Resources and Evaluation (LREC 2008).
- (van Assem et al., 2006) ⇒ Mark van Assem, Aldo Gangemi, and Guus Schreiber. (2006). “Conversion of WordNet to a standard RDF/OWL representation.” In: Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC 2006).
- (Fellbaum, 2002) ⇒ Christine Fellbaum. (2002). “On the Semantics of Troponymy.” In: The Semantics of Relationships: An Interdisciplinary. R. Green, C. Bean, and S. Myaeng (eds.). Dordrecht, Holland: Kluwer.
- The lexicon contains all those concepts to which speakers of a language attach a label (a word).
- If one examines the lexicalized concepts in relation to one another, it becomes clear that they differ in systematic ways that are characterizable in terms of similarities or contrasts. These consistent differentiations among concepts are what we call semantic relations.
- Relations are very real, though speakers may be unaware of them and may be unable to articulate them (as it the case with most metalingistic knowledge). But there are situations when one must consciously confront semantic relations. Building a lexical resource presents such a situation.
- The super-/subordinate relation, or hyponymy (or hyperonymy or ISA) relation works well to characterize the meaning of nouns, as does meronymy, the part-whose relation.
- A thesaurus lists words in semantically related groups. It is intended for users who have a certain concept in mind, and are looking either for alternative words to express this concept or for words that express similar concepts. Because its purpose is to suggest words that may be substitutable for each other, a thesaurus is necessarily organized paradigmatically. But the semantic relations between the members of a word group are not made explictly, nor are all words within a group related in the same way.
- The lexical database WordNet (George A. Miller, 1990; Fellbaum, 1998) resembles a thesaurus in that it represents word meanings primarily in terms of conceptual-semantic and lexical relations. Relations among groups of cognitively synonymous words are given straightforwardly, without being woven in the definitions, as in conventional lexicography. But unlike a standard thesaurus, the relations are transparent and explicitly labeled; moreover, they have been deliberately limited in number. The resultant structure is a large semantic network for nouns, verbs, adjectives, and adverbs.
- The bulk of WordNet, as indeed of any lexicon of English, is comprised of nouns; there are far more distinct noun forms than verbs or adjectives in the language. In constructing a semantic net of nouns, hyponymy and meronymy relations could be applied in a straightforward manner (but see George A. Miller, 1998, for details). By contrast, adjectives in many cases denote values of attributes, and can be interrelated via antonymy, as in the case of pairs hot-cold and long-short, where the antonyms express values of head and length, respectively. Most adjectives, like icy and elongated, have no salient antonyms; they are linked to core adjective like cold and long through a relation of semantic similarity (K. J. Miller, 1998).
- (Mann, 2002) ⇒ Gideon S. Mann. (2002). “Fine-Grained Proper Noun Ontologies for Question Answering.” In: Proceedings of the Worshop on Building and Using Semantic Networks (SemaNet'02) at (COLING 2002). doi:10.3115/1118735.1118746
- QUOTE: Unfortunately, building a proper noun ontology is more difficult than building a common noun ontology, since the set of proper nouns grows more rapidly. New people are born.
- (Palmer, 2000) ⇒ Martha Palmer. (2000). “Consistent Criteria for Sense Distinctions.” In: Computers and the Humanities, 34(1-2).
- (Fellbaum, 1998) ⇒ Christiane Fellbaum, editor. (1998). “WordNet: An Electronic Lexical Database and some of its Applications." MIT Press.
- WordNet, an electronic lexical database, is considered to be the most important resource available to researchers in computational linguistics, text analysis, and many related areas. Its design is inspired by current psycholinguistic and computational theories of human lexical memory. English nouns, verbs, adjectives, and adverbs are organized into synonym sets, each representing one underlying lexicalized concept. Different relations link the synonym sets.
- The purpose of this volume is twofold. First, it discusses the design of WordNet and the theoretical motivations behind it. Second, it provides a survey of representative applications, including word sense identification, information retrieval, selectional preferences of verbs, and lexical chains.
- (Leacock and Chodorow, 1998) in (Fellbaum, 1998)
- (Miller et al, 1993) ⇒ George A. Miller, R Beckwith, Christiane Fellbaum, D Gross, and Katherine J. Miller. (1993). “Introduction to WordNet: An On-line Lexical Database.” CSL Report 43, July 1990, Revised March 1993.
- (Miller et al, 1992) ⇒ George A. Miller, and Christiane Fellbaum. (1992). “Semantic Networks of English, Lexical & Conceptual Semantics.” Blackwell Publishers.