Semantic Similarity Computation for Abstract and Concrete Nouns Using Network-based Distributional Semantic Models

Motivated by cognitive lexical models, network-based distributional semantic models (DSMs) were proposed in [Iosif and Potamianos (2013)] and were shown to achieve state-of-the-art performance on semantic similarity tasks. Based on evidence for cognitive organization of concepts based on degree of concreteness, we investigate the performance and organization of network DSMs for abstract vs. concrete nouns. Results show a “concreteness effect” for semantic similarity estimation. Network DSMs that implement the maximum sense similarity assumption perform best for concrete nouns, while attributional network DSMs perform best for abstract nouns. The performance of metrics is evaluated against human similarity ratings on an English and a Greek corpus.

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

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

[3]  Dragomir R. Radev,et al.  Book Review: Graph-Based Natural Language Processing and Information Retrieval by Rada Mihalcea and Dragomir Radev , 2011, CL.

[4]  Eneko Agirre,et al.  A Study on Similarity and Relatedness Using Distributional and WordNet-based Approaches , 2009, NAACL.

[5]  Jean Véronis,et al.  HyperLex: lexical cartography for information retrieval , 2004, Comput. Speech Lang..

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

[7]  Max Coltheart,et al.  Deep Dyslexia Is Right-Hemisphere Reading , 2000, Brain and Language.

[8]  Helen M. Meng,et al.  Semiautomatic Acquisition of Semantic Structures for Understanding Domain-Specific Natural Language Queries , 2002, IEEE Trans. Knowl. Data Eng..

[9]  Alexandros Potamianos,et al.  Similarity computation using semantic networks created from web-harvested data , 2013, Natural Language Engineering.

[10]  Costanza Papagno,et al.  Reversed concreteness effect for nouns in a subject with semantic dementia , 2009, Neuropsychologia.

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

[12]  Alessandro Lenci,et al.  Distributional Memory: A General Framework for Corpus-Based Semantics , 2010, CL.

[13]  George A. Miller,et al.  Introduction to WordNet: An On-line Lexical Database , 1990 .

[14]  Uta Noppeney,et al.  Retrieval of abstract semantics , 2004, NeuroImage.

[15]  Ehud Rivlin,et al.  Placing search in context: the concept revisited , 2002, TOIS.

[16]  Eneko Agirre,et al.  Two graph-based algorithms for state-of-the-art WSD , 2006, EMNLP.

[17]  Mirella Lapata,et al.  Dependency-Based Construction of Semantic Space Models , 2007, CL.

[18]  Shrikanth S. Narayanan,et al.  Kernel Models for Affective Lexicon Creation , 2011, INTERSPEECH.

[19]  A. Paivio.  Imagery and verbal processes , 1972 .

[20]  Dominic Widdows,et al.  A Graph Model for Unsupervised Lexical Acquisition , 2002, COLING.

[21]  Philip Resnik,et al.  Using Information Content to Evaluate Semantic Similarity in a Taxonomy , 1995, IJCAI.

[22]  Alexandros Potamianos,et al.  Unsupervised Semantic Similarity Computation between Terms Using Web Documents , 2010, IEEE Transactions on Knowledge and Data Engineering.

[23]  K. Kiehl,et al.  Neural pathways involved in the processing of concrete and abstract words , 1999, Human brain mapping.