A model of synesthetic metaphor interpretation based on cross-modality similarity

Abstract Synesthesia focuses on the cross-modality connections between different perceptual modalities (visual, auditory, olfactory, gustatory, and haptic). It presents the aesthetics and creativity of our language and cognitive systems. A model that automatically interprets synesthetic metaphor is proposed in this paper. The interpretation model can learn the semantic knowledge of a feature, and simulate the cross-modality semantic similarity. The semantic knowledge has three parts: feature, the perceptual modality of the feature, and its sentimental orientation. They are used for supervising feature generation and expansion. By multi-step synonyms expansion, our model explores the cross-modality associations between the source and target domains which belong to different modalities. The appropriate feature is selected by a heuristic way to describe the latent meaning of the target domain in the current context. The experimental result shows that our model can fully consider the semantic knowledge and embody the cross-modality relations. It achieves an accuracy of 84%.

[1]  Adele E. Goldberg,et al.  Metaphorical Sentences Are More Emotionally Engaging than Their Literal Counterparts , 2014, Journal of Cognitive Neuroscience.

[2]  Rui Mao,et al.  Word Embedding and WordNet Based Metaphor Identification and Interpretation , 2018, ACL.

[3]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[4]  P. Bob,et al.  Neuroscience of synesthesia and cross-modal associations , 2014, Reviews in the neurosciences.

[5]  Chang Su,et al.  Latent semantic similarity based interpretation of Chinese metaphors , 2016, Eng. Appl. Artif. Intell..

[6]  M. Black.  More about metaphor , 1977 .

[7]  Felix Hill,et al.  Multi-Modal Models for Concrete and Abstract Concept Meaning , 2014, TACL.

[8]  Akira Utsumi,et al.  Cognitive Effects of Synesthetic Metaphors Evoked by the Semantic Interaction - eScholarship , 2009 .

[9]  Stephen Clark,et al.  Modelling metaphor with attribute-based semantics , 2017, EACL.

[10]  V. Ramachandran,et al.  Synaesthesia? A window into perception, thought and language , 2001 .

[11]  A. Henik,et al.  Bidirectionality in Synesthesia and Metaphor , 2017 .

[12]  Manaal Faruqui,et al.  Cross-lingual Models of Word Embeddings: An Empirical Comparison , 2016, ACL.

[13]  Anna Korhonen,et al.  Unsupervised Metaphor Paraphrasing using a Vector Space Model , 2012, COLING.

[14]  Dermot Lynott,et al.  Strength of perceptual experience predicts word processing performance better than concreteness or imageability , 2012, Cognition.

[15]  Gözde Özbal,et al.  Exploring Sensorial Features for Metaphor Identification , 2015 .

[16]  Gözde Özbal,et al.  Sensicon: An Automatically Constructed Sensorial Lexicon , 2014, EMNLP.

[17]  James H. Martin.  Computer Understanding of Conventional Metaphoric Language , 1992, Cogn. Sci..

[18]  Ekaterina Shutova,et al.  Automatic Metaphor Interpretation as a Paraphrasing Task , 2010, NAACL.

[19]  Jean Maillard,et al.  Black Holes and White Rabbits: Metaphor Identification with Visual Features , 2016, NAACL.

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

[21]  Tony Veale,et al.  A Fluid Knowledge Representation for Understanding and Generating Creative Metaphors , 2008, COLING.

[22]  Sean A. Day.  Synaesthesia and Synaesthetic Metaphors , 1996 .

[23]  B. Indurkhya,et al.  Metaphor and Cognition: An Interactionist Approach , 1993, CL.

[24]  Ekaterina Shutova,et al.  Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection , 2017, EMNLP.

[25]  Ken McRae,et al.  Category - Specific semantic deficits , 2008 .

[26]  Saif Mohammad,et al.  Metaphor as a Medium for Emotion: An Empirical Study , 2016, *SEMEVAL.

[27]  C. Spence,et al.  The semantic basis of taste-shape associations , 2016, PeerJ.

[28]  Matthew Purver,et al.  Modeling metaphor perception with distributional semantics vector space models , 2016, C3GI@ESSLLI.

[29]  Euripides G. M. Petrakis,et al.  Semantic similarity methods in wordNet and their application to information retrieval on the web , 2005, WIDM '05.

[30]  John A. Barnden,et al.  Modeling the interaction between sensory and affective meanings for detecting metaphor , 2015 .

[31]  Joseph M. Williams.  Synaesthetic Adjectives: A Possible Law of Semantic Change , 1976 .

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

[33]  Akira Utsumi,et al.  Computational Exploration of Metaphor Comprehension Processes Using a Semantic Space Model , 2011, Cogn. Sci..

[34]  Dermot Lynott,et al.  Modality exclusivity norms for 423 object properties , 2009, Behavior research methods.

[35]  Chang Su,et al.  Automatic detection and interpretation of nominal metaphor based on the theory of meaning , 2017, Neurocomputing.

[36]  L. Marks.  Categories of Perceptual Experience: A Psychophysicist Peruses Synesthetic Metaphors , 1983 .

[37]  B. Beck.  The Metaphor as a Mediator Between Semantic and Analogic Modes of Thought , 1978 .

[38]  S. Crutch,et al.  Defining a Conceptual Topography of Word Concreteness: Clustering Properties of Emotion, Sensation, and Magnitude among 750 English Words , 2017, Front. Psychol..

[39]  Max M. Louwerse,et al.  Symbol Interdependency in Symbolic and Embodied Cognition , 2011, Top. Cogn. Sci..