Literal and Metaphorical Senses in Compositional Distributional Semantic Models

Metaphorical expressions are pervasive in natural language and pose a substantial challenge for computational semantics. The inherent compositionality of metaphor makes it an important test case for compositional distributional semantic models (CDSMs). This paper is the first to investigate whether metaphorical composition warrants a distinct treatment in the CDSM framework. We propose a method to learn metaphors as linear transformations in a vector space and find that, across a variety of semantic domains, explicitly modeling metaphor improves the resulting semantic representations. We then use these representations in a metaphor identification task, achieving a high performance of 0.82 in terms of F-score.

[1]  Akira Utsumi.  Computational Exploration of Metaphor Comprehension Processes , 2006 .

[2]  Yulia Tsvetkov,et al.  Metaphor Detection with Cross-Lingual Model Transfer , 2014, ACL.

[3]  Joseph A. Goguen,et al.  Style: A Computational and Conceptual Blending-Based Approach , 2010, The Structure of Style.

[4]  Hinrich Schütze,et al.  Automatic Word Sense Discrimination , 1998, Comput. Linguistics.

[5]  G. Lakoff.  The Contemporary Theory of Metaphor , 1993 .

[6]  Andrew Y. Ng,et al.  Semantic Compositionality through Recursive Matrix-Vector Spaces , 2012, EMNLP.

[7]  Caroline Sporleder,et al.  Using Gaussian Mixture Models to Detect Figurative Language in Context , 2010, NAACL.

[8]  Georgiana Dinu,et al.  Improving the Lexical Function Composition Model with Pathwise Optimized Elastic-Net Regression , 2014, EACL.

[9]  Dimitri Kartsaklis,et al.  Separating Disambiguation from Composition in Distributional Semantics , 2013, CoNLL.

[10]  Yair Neuman,et al.  Literal and Metaphorical Sense Identification through Concrete and Abstract Context , 2011, EMNLP.

[11]  Jeffrey Pennington,et al.  Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions , 2011, EMNLP.

[12]  James H. Martin,et al.  Topic Model Analysis of Metaphor Frequency for Psycholinguistic Stimuli , 2009, HLT-NAACL 2009.

[13]  Mirella Lapata,et al.  Vector-based Models of Semantic Composition , 2008, ACL.

[14]  L. Cameron.  Metaphor in Educational Discourse , 2003 .

[15]  E. Guevara.  A Regression Model of Adjective-Noun Compositionality in Distributional Semantics , 2010 .

[16]  Louise McNally,et al.  First Order vs. Higher Order Modification in Distributional Semantics , 2012, EMNLP-CoNLL.

[17]  D. Barr,et al.  Random effects structure for confirmatory hypothesis testing: Keep it maximal. , 2013, Journal of memory and language.

[18]  Jonathan Dunn,et al.  Evaluating the Premises and Results of Four Metaphor Identification Systems , 2013, CICLing.

[19]  John Bryant,et al.  Catching Metaphors , 2006 .

[20]  Caroline Sporleder,et al.  Unsupervised Recognition of Literal and Non-Literal Use of Idiomatic Expressions , 2009, EACL.

[21]  Steven Bird,et al.  NLTK: The Natural Language Toolkit , 2002, ACL.

[22]  Yulia Tsvetkov,et al.  Cross-Lingual Metaphor Detection Using Common Semantic Features , 2013 .

[23]  M. Louwerse,et al.  Language statistics and individual differences in processing primary metaphors , 2013 .

[24]  Xiaojin Zhu,et al.  Hunting Elusive Metaphors Using Lexical Resources. , 2007 .

[25]  Joachim Lambek,et al.  Type Grammar Revisited , 1997, LACL.

[26]  Joseph A. Goguen,et al.  7 Information visualisation and semiotic morphisms , 2005 .

[27]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[28]  Barbara H. Partee,et al.  Lexical semantics and compositionality. , 1995 .

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

[30]  Marco Baroni,et al.  Frege in Space: A Program for Composition Distributional Semantics , 2014, LILT.

[31]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[32]  J. Goguen.  An introduction to algebraic semiotics, with application to user interface design , 1999 .

[33]  Mark Last,et al.  Metaphor Identification in Large Texts Corpora , 2013, PloS one.

[34]  Richard Montague,et al.  ENGLISH AS A FORMAL LANGUAGE , 1975 .

[35]  George Lakoff,et al.  Some Empirical Results about the Nature of Concepts , 1989 .

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

[37]  Marco Baroni,et al.  Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space , 2010, EMNLP.

[38]  Tomek Strzalkowski,et al.  Robust Extraction of Metaphor from Novel Data , 2013 .

[39]  Jonathan Dunn.  What metaphor identification systems can tell us about metaphor-in-language , 2013 .

[40]  Ralph Weischedel,et al.  Automatic Extraction of Linguistic Metaphors with LDA Topic Modeling , 2013 .

[41]  B. Everitt,et al.  Large sample standard errors of kappa and weighted kappa. , 1969 .

[42]  Caroline Sporleder,et al.  Classifier Combination for Contextual Idiom Detection Without Labelled Data , 2009, EMNLP.

[43]  Bodo Winter,et al.  Of magnitudes and metaphors: Explaining cognitive interactions between space, time, and number , 2015, Cortex.

[44]  Eduard Hovy,et al.  Identifying Metaphorical Word Use with Tree Kernels , 2013 .

[45]  Tomek Strzalkowski,et al.  Robust Extraction of Metaphors from Novel Data , 2013 .

[46]  Peter D. Turney.  Distributional Semantics Beyond Words: Supervised Learning of Analogy and Paraphrase , 2013, TACL.

[47]  Anna Korhonen,et al.  Metaphor Identification Using Verb and Noun Clustering , 2010, COLING.

[48]  Ekaterina Shutova,et al.  Design and Evaluation of Metaphor Processing Systems , 2015, CL.

[49]  Patrick Pantel,et al.  Discovering word senses from text , 2002, KDD.

[50]  Daniel Fried,et al.  Low-Rank Tensors for Verbs in Compositional Distributional Semantics , 2015, ACL.

[51]  Yuji Matsumoto,et al.  Modeling and Learning Semantic Co-Compositionality through Prototype Projections and Neural Networks , 2013, EMNLP.

[52]  David I. Spivak.  Category Theory for the Sciences , 2014 .

[53]  G. Lakoff,et al.  Metaphors We Live by , 1981 .

[54]  Andrew U. Frank,et al.  A Formalization of Metaphors and Image-Schemas in User Interfaces , 1991 .

[55]  Stephen Clark,et al.  Mathematical Foundations for a Compositional Distributional Model of Meaning , 2010, ArXiv.

[56]  Gerard J. Steen,et al.  A method for linguistic metaphor identification : from MIP to MIPVU , 2010 .

[57]  Anoop Sarkar,et al.  A Clustering Approach for Nearly Unsupervised Recognition of Nonliteral Language , 2006, EACL.

[58]  Dimitri Kartsaklis,et al.  Prior Disambiguation of Word Tensors for Constructing Sentence Vectors , 2013, EMNLP.

[59]  Sterling Hutchinson,et al.  Language statistics explain the spatial–numerical association of response codes , 2014, Psychonomic bulletin & review.

[60]  G. Lakoff,et al.  Metaphors We Live by , 1982 .

[61]  Caroline Sporleder,et al.  Topic Models for Word Sense Disambiguation and Token-Based Idiom Detection , 2010, ACL.

[62]  D. Casasanto,et al.  Development of Metaphorical Thinking: The Role of Language , 2016 .

[63]  Michael Mohler,et al.  Semantic Signatures for Example-Based Linguistic Metaphor Detection , 2013 .

[64]  Georgiana Dinu,et al.  General estimation and evaluation of compositional distributional semantic models , 2013, CVSM@ACL.