Skip to main content
Log in

Large, huge or gigantic? Identifying and encoding intensity relations among adjectives in WordNet

  • Original Paper
  • Published:
Language Resources and Evaluation Aims and scope Submit manuscript

An Erratum to this article was published on 02 June 2013

Abstract

We propose a new semantic relation for gradable adjectives in WordNet, which enriches the present, vague, similar relation with information on the degree or intensity with which different adjectives express a shared attribute. Using lexical-semantic patterns, we mine the Web for evidence of the relative strength of adjectives like “large”, “huge” and “gigantic” with respect to their attribute (“size”). The pairwise orderings we derive allow us to construct scales on which the adjectives are located. To represent the intensity relation among gradable adjectives in WordNet, we combine ordered scales with the current WordNet dumbbells based on the relation between a pair of central adjectives and a group of undifferentiated semantically similar adjectives. A new intensity relation links the adjectives in the dumbbells and their concurrent representation on scales. Besides capturing the semantics of gradable adjectives in a way that is both intuitively clear as well as consistent with corpus data, the introduction of an intensity relation would potentially result in several specific benefits for NLP.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Notes

  1. Roget’s thesaurus, first released in 1852, also represents the adjectives in terms of antonyms and semantically similar adjectives, though not in the “dumbbell” structure found in WordNet’s.

  2. Of course, substitution here implies only similarity, not identity of meaning.

  3. Note that adjectives that encode different values of a shared attribute also show distributional similarity, as in contexts such as “our trip to the Grand Canyon was good/great/fabulous”.

  4. df represents document frequency.

  5. threshold regulates the number of pages returned by the search engine that is considered sufficient to trust the result, and it was set to 20 in this work.

  6. weight regulates the gap between s 1 over s 2 that is required to prefer one over the other, and it was set to 15 in this work.

  7. http://www.ids-mannheim.de/cosmas2.

  8. F 2 score is the harmonic mean of precision and recall with additional weight placed on recall.

  9. Currently, WordNet encodes entailment relations among some verbs, but it doesn’t provide a distinction between finer-grained subtypes such as backward presupposition (“know” must happen before “forget”) versus temporal inclusion (“step” is part of the action of “walk”) (Fellbaum et al. 1993). Extracting instances of specific fine-grained relations, including intensity (may \(\rightarrow\) should \(\rightarrow\) must) using computational methods such as those in VerbOcean (Chklovski and Pantel 2004) may be considered for further enrichment of WordNet.

References

  • Bierwisch, M. (1989). The semantics of gradation. In M. Bierwisch & E. Lang (Eds.), Dimensional adjectives (pp. 71–261). Berlin: Springer.

  • Chklovski, T., & Pantel, P. (2004). Verbocean: Mining the web for fine-grained semantic verb relations. In Proceedings of the Conference on empirical methods in natural language processing (EMNLP-04), Barcelona, Spain, pp. 33–40.

  • Church, K., & Hanks, P. (1988). Word association norms, mutual information and lexicography. Computational Linguistics, 16, 1–8.

    Google Scholar 

  • Clark, P., Murray, W. R., Thompson, J., Harrison, P., Hobbs, J., & Fellbaum, C. (2007). On the role of lexical and world knowledge in rte3. In Proceedings of the ACL-PASCAL workshop on textual entailment and paraphrasing, association for computational linguistics, Stroudsburg, PA, USA, RTE ’07, pp. 54–59.

  • Clark, P., Fellbaum, C., Hobbs, J., Harrison, P., Murray, W., & Thompson, J. (2008). Augmenting wordnet for deep understanding of text. In Proceedings of the 2008 conference on semantics in text processing, association for computational linguistics, Stroudsburg, PA, USA, STEP ’08, pp. 45–57.

  • Collins, A. M., & Quillian, M. R. (1969). Retrieval time from semantic memory. Journal of Verbal Learning and Verbal Behavior, 8, 240–247.

    Article  Google Scholar 

  • Cruse, D. A. (1986). Lexical semantics. New York: Cambridge University Press.

    Google Scholar 

  • Davidov, D., & Rappoport, A. (2008). Unsupervised discovery of generic relationships using pattern clusters and its evaluation by automatically generated SAT analogy questions. In Proceedings of the ACL-08, HLT, association for computational linguistics, Columbus, Ohio, pp. 692–700.

  • Deese, J. (1964). The associative structure of some common english adjectives. Journal of Verbal Learning and Verbal Behavior, 3(5), 347–357.

    Article  Google Scholar 

  • Edmonds, P. (1999). Semantic representation of near-synonyms for automatic lexical choice. PhD thesis, University of Toronto.

  • Esuli, A. E. A., & Sebastiani, F. (2006). Sentiwordnet: A publicly available lexical resource for opinion mining. In Proceedings of the LREC-06, 5th conference on language resources and evaluation, Genova, IT, pp. 417–422.

  • Fellbaum, C. (1998). WordNet : An electronic lexical database. MIT Press: Cambridge.

    Google Scholar 

  • Fellbaum, C. (2002). Parallel hierarchies in the verb lexicon. In K. Simov (Ed.), Proceedings of the Ontolex02 workshop on ontologies and lexical knowledge bases (pp. 27–31). Paris: ELRA.

  • Fellbaum, C., Gross, D., & Miller, K. (1993). Adjectives in wordnet. In G. A. Miller, C. Fellbaum & K. J. Miller (Eds.), Five papers on WordNet. Princeton University, Cognitive Science Laboratory, Princeton, USA. http://wordnetcode.princeton.edu/5papers.pdf

  • Fellbaum, C., Clark, P., & Hobbs, J. (2008). Towards improved text understanding with wordnet. In A. Storrer, A. Geyken, A. Siebert & K. M. Würzner (Eds.), Text resources and lexical knowledge. Berlin: Mouton de Gruyter.

  • Gross, D., Fischer, U., & Miller, G. A. (1989). Antonyms and the representation of adjectival meanings. Journal of Memory and Language, 28(1), 92–106.

    Article  Google Scholar 

  • Hamp, B., & Feldweg, H. (1997). Germanet—a lexical–semantic net for german. In Proceedings of the ACL workshop automatic information extraction and building of lexical semantic resources for NLP Applications, pp. 9–15.

  • Hartung, M., & Frank, A. (2010). A structured vector space model for hidden attribute meaning in adjective-noun phrases. In Proceedings of the 23rd international conference on computational linguistics.

  • Hatzivassiloglou, V., & McKeown, K. R. (1993). Towards the automatic identification of adjectival scales: Clustering adjectives according to meaning. In Proceedings of the 31st annual meeting on association for computational linguistics, ACL, association for computational linguistics, Morristown, NJ, USA, pp. 172–182.

  • Hatzivassiloglou, V., & McKeown, K. R. (1997). Predicting the semantic orientation of adjectives. In Proceedings of the Eighth conference on European chapter of the association for computational linguistics (ACL-97), pp. 174–181.

  • Hearst, M. (1992). Automatic acquisition of hyponyms from large text corpora. In Proceedings of the 14th conference on computational linguistics (COLING-92), pp. 539–545.

  • Inkpen, D., & Hirst, G. (2006). Building and using a lexical knowledge base of near-synonym differences. Computational Linguistics, 32(2), 223–262.

    Article  Google Scholar 

  • Jindal, N., & Liu, B. (2008). Opinion spam and analysis. In Proceedings of the international conference on Web search and web data mining, ACM, New York, NY, USA, WSDM ’08, pp. 219–230.

  • Julien, I. (2010). Linguistic analysis with adjscales as a tool for predicting spam product reviews. Tech. rep., Department of Computer Science. Princeton University.

  • Julien, I. (2011). Automatically determining implications between adjectives. Tech. rep., Department of Computer Science. Princeton University.

  • Justeson, J. S., & Katz, S. M. (1991). Co-occurrences of antonymous adjectives and their contexts. Computational Linguistics, 17, 1–19.

    Google Scholar 

  • Kennedy, C. (2001). Polar opposition and the ontology of degrees. Linguistics and Philosophy, 24, 33–70.

    Article  Google Scholar 

  • Kilgarriff, A. (2007). Googleology is bad science. Computational Linguistics, 33(1), 147–151.

    Article  Google Scholar 

  • Lin, D. (1998). Automatic retrieval and clustering of similar words. In Proceedings of the 17th international conference on computational linguistics, association for computational linguistics, Morristown, NJ, USA (Vol. 2), pp. 768–774.

  • Miller, G. A. (1995). Wordnet: A lexical database for english. ACM, 38(11), 39–41.

    Article  Google Scholar 

  • Moss, H., & Older, L. (1996). Word association norms. Hove, U. K.: Psychology Press.

    Google Scholar 

  • Patwardhan, S., Banerjeev, S., & Pedersen, T. (2005). Senserelate::targetword—a generalized framework for word sense disambiguation. In Proceedings of the twentieth national conference on artificial intelligence.

  • Riloff, E., & Jones, R. (1999). Learning dictionaries for information extraction by multi-level bootstrapping. In Proceedings of the 16th national conference on artificial intelligence (AAAI-99).

  • Schulam, P. (2011). Scle: A system for automatically comparing gradable adjectives, senior Thesis.

  • Schulam, P. F., & Fellbaum, C. (2010). Automatically determining the semantic gradation of german adjectives. In Semantic Approaches to Natural Language Proceedings, Saarbruecken, Germany, p. 163.

  • Sheinman, V., & Tokunaga, T. (2009a). Adjscales: Differentiating between similar adjectives for language learners. In Proceedings of the International conference on computer supported education (CSEDU-09).

  • Sheinman, V., & Tokunaga, T. (2009b). Adjscales: Visualizing differences between adjectives for language learners. IEICE Transactions on Information and Systems, E92-D(8), 1542–1550.

    Article  Google Scholar 

  • Snow, R., Jurafsky, D., & Ng, A. (2005). Learning syntactic patterns for automatic hypernym discovery. Advances in neural information processing systems, 17, 1297–1304.

    Google Scholar 

  • Turney, P. D. (2008). A uniform approach to analogies, synonyms, antonyms, and associations. In Proceedings of the 22nd international conference on computational linguistics (Coling 2008), Manchester, UK.

  • Weeds, J., & Weir, D. (2005). Co-occurrence retrieval: A flexible framework for lexical distributional similarity. Computational Linguistics, 31(4), 439–475.

    Article  Google Scholar 

  • Wilks, Y., & Brewster, C. (2009). Natural language processing as a foundation of the semantic Web. Hanover: Now Publishers Inc.

    Google Scholar 

Download references

Acknowledgments

Fellbaum, Julien and Schulam were supported by grants from the U.S. National Science Foundation (CNS 0855157, IIS 1139844 and CCF 0937139).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Vera Sheinman.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Sheinman, V., Fellbaum, C., Julien, I. et al. Large, huge or gigantic? Identifying and encoding intensity relations among adjectives in WordNet. Lang Resources & Evaluation 47, 797–816 (2013). https://doi.org/10.1007/s10579-012-9212-1

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10579-012-9212-1

Keywords

Navigation