Inclusive yet Selective: Supervised Distributional Hypernymy Detection

We test the Distributional Inclusion Hypothesis, which states that hypernyms tend to occur in a superset of contexts in which their hyponyms are found. We find that this hypothesis only holds when it is applied to relevant dimensions. We propose a robust supervised approach that achieves accuracies of .84 and .85 on two existing datasets and that can be interpreted as selecting the dimensions that are relevant for distributional inclusion.

[1]  Philipp Cimiano,et al.  Ontology Learning from Text: Methods, Evaluation and Applications , 2005 .

[2]  Alessandro Lenci,et al.  Identifying hypernyms in distributional semantic spaces , 2012, *SEMEVAL.

[3]  Ido Dagan,et al.  Articles: Bootstrapping Distributional Feature Vector Quality , 2009, CL.

[4]  Raffaella Bernardi,et al.  Entailment above the word level in distributional semantics , 2012, EACL.

[5]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[6]  Marti A. Hearst.  Automatic Acquisition of Hyponyms from Large Text Corpora , 1992, COLING.

[7]  Dan I. Moldovan,et al.  Learning Semantic Constraints for the Automatic Discovery of Part-Whole Relations , 2003, NAACL.

[8]  Peter D. Turney.  Similarity of Semantic Relations , 2006, CL.

[9]  Patrick Pantel,et al.  Espresso: Leveraging Generic Patterns for Automatically Harvesting Semantic Relations , 2006, ACL.

[10]  David J. Weir,et al.  Characterising Measures of Lexical Distributional Similarity , 2004, COLING.

[11]  Alessandro Lenci,et al.  How we BLESSed distributional semantic evaluation , 2011, GEMS.

[12]  Steffen Staab,et al.  Learning Taxonomic Relations from Heterogeneous Sources of Evidence , 2005 .

[13]  Daniel Jurafsky,et al.  Learning Syntactic Patterns for Automatic Hypernym Discovery , 2004, NIPS.

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

[15]  David J. Weir,et al.  A General Framework for Distributional Similarity , 2003, EMNLP.

[16]  Thomas L. Griffiths,et al.  Contextual Dependencies in Unsupervised Word Segmentation , 2006, ACL.

[17]  Aurélie Herbelot,et al.  Measuring semantic content in distributional vectors , 2013, ACL.

[18]  Daniel Jurafsky,et al.  Semantic Taxonomy Induction from Heterogenous Evidence , 2006, ACL.

[19]  Dan I. Moldovan,et al.  Automatic Discovery of Part-Whole Relations , 2006, CL.

[20]  Eugene Charniak,et al.  Finding Parts in Very Large Corpora , 1999, ACL.

[21]  Patrick Pantel,et al.  VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations , 2004, EMNLP.

[22]  Daoud Clarke.  Context-theoretic Semantics for Natural Language: an Overview , 2009 .

[23]  Ido Dagan,et al.  Directional distributional similarity for lexical inference , 2010, Natural Language Engineering.

[24]  Alessandro Lenci,et al.  Distributional semantics in linguistic and cognitive research , 2008 .

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

[26]  Ido Dagan,et al.  The Distributional Inclusion Hypotheses and Lexical Entailment , 2005, ACL.

[27]  Dekang Lin,et al.  An Information-Theoretic Definition of Similarity , 1998, ICML.

[28]  Ido Dagan,et al.  Feature Vector Quality and Distributional Similarity , 2004, COLING.

[29]  Silvia Bernardini,et al.  The WaCky wide web: a collection of very large linguistically processed web-crawled corpora , 2009, Lang. Resour. Evaluation.

[30]  Geoffrey Zweig,et al.  Linguistic Regularities in Continuous Space Word Representations , 2013, NAACL.

[31]  G. Murphy,et al.  The Big Book of Concepts , 2002 .