Uncovering Distributional Differences between Synonyms and Antonyms in a Word Space Model

For many NLP applications such as Information Extraction and Sentiment Detection, it is of vital importance to distinguish between synonyms and antonyms. While the general assumption is that distributional models are not suitable for this task, we demonstrate that using suitable features, differences in the contexts of synonymous and antonymous German adjective pairs can be identified with a simple word space model. Experimenting with two context settings (a simple windowbased model and a ‘co-disambiguation model’ to approximate adjective sense disambiguation), our best model significantly outperforms the 50% baseline and achieves 70.6% accuracy in a synonym/antonym classification task.

[1]  Ming Zhou,et al.  Identifying Synonyms among Distributionally Similar Words , 2003, IJCAI.

[2]  Carita Paradis,et al.  Antonyms in context , 2001 .

[3]  J. Deese.  The structure of associations in language and thought , 1966 .

[4]  Graeme Hirst,et al.  Evaluating WordNet-based Measures of Lexical Semantic Relatedness , 2006, CL.

[5]  Carita Paradis,et al.  Good and bad opposites: using textual and experimental techniques to measure antonym canonicity , 2009 .

[6]  Gemma Boleda,et al.  Modeling Regular Polysemy: A Study on the Semantic Classification of Catalan Adjectives , 2012, CL.

[7]  Julie Weeds,et al.  Unsupervised Acquisition of Predominant Word Senses , 2007, CL.

[8]  Christopher D. Manning,et al.  Finding Contradictions in Text , 2008, ACL.

[9]  Zellig S. Harris,et al.  Distributional Structure , 1954 .

[10]  Donald Hindle,et al.  Noun Classification From Predicate-Argument Structures , 1990, ACL.

[11]  G. Miller,et al.  Contextual correlates of semantic similarity , 1991 .

[12]  Geoffrey Zweig,et al.  Polarity Inducing Latent Semantic Analysis , 2012, EMNLP.

[13]  Bernd Bohnet,et al.  Top Accuracy and Fast Dependency Parsing is not a Contradiction , 2010, COLING.

[14]  G. Murphy,et al.  The Conceptual Basis of Antonymy and Synonymy in Adjectives , 1993 .

[15]  Patrick Pantel,et al.  From Frequency to Meaning: Vector Space Models of Semantics , 2010, J. Artif. Intell. Res..

[16]  L. Murphy.  Semantic Relations and the Lexicon , 2003 .

[17]  Graeme Hirst,et al.  Computing Lexical Contrast , 2013, CL.

[18]  Jason Eisner,et al.  Lexical Semantics , 2020, The Handbook of English Linguistics.

[19]  Graeme Hirst,et al.  Determining Word Sense Dominance Using a Thesaurus , 2006, EACL.

[20]  Dekang Lin,et al.  Automatic Retrieval and Clustering of Similar Words , 1998, ACL.

[21]  Katrin Erk,et al.  Representing words as regions in vector space , 2009, CoNLL.

[22]  G. Miller,et al.  Contexts of antonymous adjectives , 1989, Applied Psycholinguistics.

[23]  Katrin Erk,et al.  Exemplar-Based Models for Word Meaning in Context , 2010, ACL.

[24]  Raymond J. Mooney,et al.  Multi-Prototype Vector-Space Models of Word Meaning , 2010, NAACL.

[25]  Peter D. Turney.  A Uniform Approach to Analogies, Synonyms, Antonyms, and Associations , 2008, COLING.

[26]  Magnus Sahlgren,et al.  The Word-Space Model: using distributional analysis to represent syntagmatic and paradigmatic relations between words in high-dimensional vector spaces , 2006 .

[27]  Katrin Erk,et al.  Vector Space Models of Word Meaning and Phrase Meaning: A Survey , 2012, Lang. Linguistics Compass.

[28]  Ulrich Heid,et al.  Design and Application of a Gold Standard for Morphological Analysis: SMOR as an Example of Morphological Evaluation , 2010, LREC.

[29]  Philip Edmonds,et al.  Choosing the Word Most Typical in Context Using a Lexical Co-occurrence Network , 1997, ACL.

[30]  Slava M. Katz,et al.  Co-Occurrences of Antonymous Adjectives and Their Contexts , 1991, Comput. Linguistics.

[31]  John B. Goodenough,et al.  Contextual correlates of synonymy , 1965, CACM.