-
Notifications
You must be signed in to change notification settings - Fork 0
EnglishLexicalResources
Code for English lexical resources is located in "core" project. The actual resources code is in sub-packages of eu.excitementproject.eop.core.component.lexicalknowledge.
Resource name: Dekang Lin's dependency-based thesaurus
Implementation: LinDependencyOriginalLexicalResourse
Resource description: Resource was downloaded from Dekang Lin's website, http://webdocs.cs.ualberta.ca/~lindek/downloads.htm, but is not available there anymore. "Dependency-based thesaurus. This contains a list automatically constructed thesaurus. For each word, the thesaurus lists up to 200 most similar words and their similarities. The similar words are clustered (also automatically)."
POS: nouns (n), verbs (v), adjectives & adverbs (a)
Ref to relevant Paper: “Automatic Retrieval and Clustering of Similar Words”, Dekang Lin, COLING-ACL, 1998, pp. 768-774.
DB Scheme: lin (qa-srv:3308)
DB tables: lin_dep_n, lin_dep_v, lin_dep_a
Resource name: Dekang Lin's proximity-based thesaurus
Implementation: LinProximityOriginalLexicalResource
Resource description: Resource is available for download from Dekang Lin's website, http://webdocs.cs.ualberta.ca/~lindek/downloads.htm. "Proximity-based thesaurus. Similar to the dependency-based thesaurus. But the words similarity is computed based on the linear proximity relationship between words only, where as the above thesaurus used dependency relationships extracted from a parsed corpus."
POS: nouns (n), verbs (v), adjectives & adverbs (a)
Ref to relevant Paper: “Automatic Retrieval and Clustering of Similar Words”, Dekang Lin, COLING-ACL, 1998, pp. 768-774.
DB Scheme: lin (qa-srv:3308)
DB tables: lin_proximity
Resource name: Lin distributional similarity for Reuters
Implementation: LinDistsimLexicalResource
Resource description: A resourse of distributional similarity rules calculated with Idan's dist.sim. code using Lin's measure (without clustering) over the Reuters RCV1 corpus with dependency-based features.
POS: nouns
Ref to relevant Paper: “Automatic Retrieval and Clustering of Similar Words”, Dekang Lin, COLING-ACL, 1998, pp. 768-774.
DB Scheme: distsim (qa-srv:3308)
DB tables: lin_rules_lemmas
Resource name: DIRECT-200 / DIRECT-1000
Implementation: Direct200LexicalResource / Direct1000LexicalResource
Resource description: Directional similarity rules calculated using the balancedAP (bap) measure over Reuters RCV1 corpus with dependency-based features. Downloabable from our homepage (http://u.cs.biu.ac.il/~nlp/downloads/DIRECT.html)
Direct1000LexicalResource - up to 1000 similarity rules per right-hand-side term (nouns and verbs)
Direct200LexicalResource - a part from the above, limited to up to 200 rules per term
POS: nouns & verbs
Ref to relevant Paper:
(1) Lili Kotlerman, Ido Dagan, Idan Szpektor and Maayan Zhitomirsky-Geffet. Directional Distributional Similarity for Lexical Inference. Special Issue of Natural Language Engineering on Distributional Lexical Semantics (JNLE-DLS), 2010.
(2) Lili Kotlerman, Ido Dagan, Idan Szpektor and Maayan Zhitomirsky-Geffet. Directional Distributional Similarity for Lexical Expansion. In Proceedings of ACL (short papers), 2009.
DB Scheme: bap (qa-srv:3308)
DB tables: direct_nouns_200, direct_verbs_200 / direct_nouns_1000, direct_verbs_1000
Resource name: WordNet
Implementation: WordnetLexicalResource
Resource description: Uses WordNet relations which correspond to lexical entailment.
Ref to relevant Paper: Fellbaum, Christiane, ed. 1998. WordNet An Electronic Lexical Database. The MIT Press.
Resource name: Wiktionary
Implementation: WiktionaryLexicalResource
Resource description: Uses Wikitionary relations to retrieve lexical entailment. See http://en.wiktionary.org/wiki/Wiktionary:Main_Page
Resource name: Wikipedia
Implementation: WikiLexicalResourcee
Resource description: Lexical rules that were extracted automatically from English Wikipedia
Ref to relevant Paper: Eyal Shnarch, Libby Barak, Ido Dagan. Extracting Lexical Reference Rules from Wikipedia. ACL, 2009.
Resource name: VerbOcean
Implementation: VerbOceanLexicalResource
Resource description: Extract lexical entailment rules from VerbOcean.
Ref to relevant Paper: Timothy Chklovski and Patrick Pantel. 2004.VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations. In Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP-04). Barcelona, Spain.
Resource name: Catvar
Implementation: CatvarLexicalResource
Resource description: Extract lexical entailment rules from CatVar
Ref to relevant Paper: Habash, Nizar and Bonnie Dorr, A Categorial Variation Database for English, Proceedings of the North American Association for Computational Linguistics, Edmonton, Canada, pp. 96--102, 2003