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

Sheinman, Vera; Fellbaum, Christiane; Julien, Isaac; Schulam, Peter; Tokunaga, Takenobu

doi:10.1007/s10579-012-9212-1

Cited by 13 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kim and de Marneffe (2013) also obtain an ordering given a pair of adjectives, using distributional word vectors derived from a recursive neural network. Sheinman et al (2013) and de Melo and Bansal (2013) present similar approaches, which make use of WordNet dumbbells to determine words that belong to the same scale as proposed in Sheinman et al (2012). A WordNet dumbbell is a representation involving an antonym pair (e.g., small and large) as two ends of a semantic scale with semantically similar adjectives arranged in a radial fashion around each adjective.…”

Section: Related Workmentioning

confidence: 99%

“…This is primarily because of polysemy and semantic drift (de Melo and Bansal, 2013). Sheinman et al (2013) present a two-step approach for establishing an ordering among scalar adjectives. They extract adjectives from the Web using lexical patterns indicative of the direction of the scalar relationship between a pair of adjectives.…”

Section: Related Workmentioning

confidence: 99%

“…de Melo and Bansal (2013) improve upon Sheinman et al (2013) by refining their lexical patterns, and refer to them as "strong-weak" and "weakstrong" patterns. Using frequencies of occurrence for a pair of adjectives across the strong-weak and weak-strong patterns in a corpus, they define an overall weak-strong score.…”

Section: Related Workmentioning

confidence: 99%

“…This is because these patterns consist of longer n-grams, which are sparsely found in a small dataset. Therefore, Sheinman et al (2013) use the Web as their corpus, and de Melo & Bansal use Google N-grams (Brants and Franz, 2006). However, this results in a large number of instances where satisfied lexical patterns do not correspond to adjectives (e.g., sometimes but not always).…”

Section: Related Workmentioning

confidence: 99%

“…Recently, there has been a lot of interest in exploring different approaches to derive an ordering among gradable adjectives based on their semantics (Ruppenhofer et al, 2014;Sheinman et al, 2013;Schulam and Fellbaum, 2010). de Melo and Bansal (2013) propose a novel Mixed Integer Linear Programming (MILP) based approach, publish a gold standard dataset and report the best performance on ordering scalar adjectives on this dataset.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Corpus-based discovery of semantic intensity scales

Shivade

Marneffe

Fosler‐Lussier

et al. 2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Gradable terms such as brief, lengthy and extended illustrate varying degrees of a scale and can therefore participate in comparative constructs. Knowing the set of words that can be compared on the same scale and the associated ordering between them (brief < lengthy < extended) is very useful for a variety of lexical semantic tasks. Current techniques to derive such an ordering rely on WordNet to determine which words belong on the same scale and are limited to adjectives. Here we describe an extension to recent work: we investigate a fully automated pipeline to extract gradable terms from a corpus, group them into clusters reflecting the same scale and establish an ordering among them. This methodology reduces the amount of required handcrafted knowledge, and can infer gradability of words independent of their part of speech. Our approach infers an ordering for adjectives with comparable performance to previous work, but also for adverbs with an accuracy of 71%. We find that the technique is useful for inferring such rankings among words across different domains, and present an example using biomedical text.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Corpus-based discovery of semantic intensity scales

Shivade

Marneffe

Fosler‐Lussier

et al. 2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

A Semi-automatic Adjective Mapping Between plWordNet and Princeton WordNet

Rudnicka

Witkowski

Kaliński

2015

Text, Speech, and Dialogue

View full text Add to dashboard Cite

The paper presents the strategy and results of mapping adjective synsets between plWordNet (the wordnet of Polish, cf. Piasecki et al. 2009, Maziarz et al. 2013) and Princeton WordNet (cf. Fellbaum 1998. The main challenge of this enterprise has been very different synset relation structures in the two networks: horizontal, dumbbell-model based in PWN and vertical, hyponymy-based in plWN.Moreover, the two wordnets display differences in the grouping of adjectives into semantic domains and in the size of the adjective category. The handle the above contrasts, a series of automatic prompt algorithms and a manual mapping procedure relying on corresponding synset and lexical unit relations as well as on inter-lingual relations between noun synsets were proposed in the pilot stage of mapping (Rudnicka et al. 2015). In the paper we discuss the final results of the mapping process as well as explain example mapping choices. Suggestions for further development of mapping are also given.

show abstract

Large-scale Lexicography in the Digital Age

Fellbaum¹

2014

International Journal of Lexicography

View full text Add to dashboard Cite

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

Cited by 13 publications

References 17 publications

Corpus-based discovery of semantic intensity scales

Corpus-based discovery of semantic intensity scales

A Semi-automatic Adjective Mapping Between plWordNet and Princeton WordNet

Large-scale Lexicography in the Digital Age

Contact Info

Product

Resources

About