Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

9

EMNLP
2008

favoriteEmaildiscussreport

90views Natural Language Processing» more EMNLP 2008»

Computing Word-Pair Antonymy

13 years 6 months ago

Computing Word-Pair Antonymy

Download www.umiacs.umd.edu

Knowing the degree of antonymy between words has widespread applications in natural language processing. Manually-created lexicons have limited coverage and do not include most semantically contrasting word pairs. We present a new automatic and empirical measure of antonymy that combines corpus statistics with the structure of a published thesaurus. The approach is evaluated on a set of closest-opposite questions, obtaining a precision of over 80%. Along the way, we discuss what humans consider antonymous and how antonymy manifests itself in utterances.

Saif Mohammad, Bonnie J. Dorr, Graeme Hirst

Real-time Traffic

EMNLP 2008 | Manually-created Lexicons | Natural Language Processing | Widespread Applications |

claim paper

Related Content

» Review spotlight a user interface for summarizing usergenerated reviews using adjectivenou...

» Dependency Parsing and Projection Based on WordPair Classification

» Phylogenetically and spatially conserved word pairs associated with gene expression change...

» Applying an NVEF WordPair Identifier to the Chinese SyllabletoWord Conversion Problem

» Antonymy and Conceptual Vectors

» Measuring Semantic Similarity in the Taxonomy of WordNet

» Weakly Supervised Learning of Presupposition Relations between Verbs

» An Algorithm for Unsupervised Transliteration Mining with an Application to Word Alignment

» Using Lexical and Relational Similarity to Classify Semantic Relations

Post Info
More Details (n/a)

Added	29 Oct 2010
Updated	29 Oct 2010
Type	Conference
Year	2008
Where	EMNLP
Authors	Saif Mohammad, Bonnie J. Dorr, Graeme Hirst

Comments (0)