Lexical and affective models in early acquisition of semantics

Motivated by theories of early language development in children we investigate the contribution of affective features to early acquisition of lexical semantics. For the task of semantic similarity between words, semantic and affective spaces are modeled using network-based distributed semantic models. We propose a method for constructing semantic activations from a combination of lexical and affective relations and show that affective information plays a prominent role in our lexical development model.

[1]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[2]  Elia Bruni,et al.  Multimodal Distributional Semantics , 2014, J. Artif. Intell. Res..

[3]  Elias Iosif,et al.  Network-based distributional semantic models , 2013 .

[4]  Lori Markson,et al.  Capacities underlying word learning , 1998, Trends in Cognitive Sciences.

[5]  Alexandros Potamianos,et al.  Cognitively Motivated Distributional Representations of Meaning , 2016, LREC.

[6]  Linda B. Smith,et al.  Object Shape, Object Function, and Object Name , 1998 .

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

[8]  M. Tomasello,et al.  Understanding and sharing intentions: The origins of cultural cognition , 2005, Behavioral and Brain Sciences.

[9]  Michael L. Littman,et al.  Measuring praise and criticism: Inference of semantic orientation from association , 2003, TOIS.

[10]  Stevan Harnad.  The Symbol Grounding Problem , 1999, ArXiv.

[11]  T. Regier.  Emergent constraints on word-learning: a computational perspective , 2003, Trends in Cognitive Sciences.

[12]  Chunyu Kit,et al.  How Does Lexical Acquisition Begin? A cognitive perspective , 2003 .

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

[14]  Shrikanth S. Narayanan,et al.  Therapy language analysis using automatically generated psycholinguistic norms , 2015, INTERSPEECH.

[15]  Alexandros Potamianos,et al.  SemSim: Resources for Normalized Semantic Similarity Computation Using Lexical Networks , 2012, LREC.

[16]  Ping Li,et al.  The Acquisition of Word Meaning through Global Lexical Co-occurrences , 2000 .

[17]  Preslav Nakov,et al.  SemEval-2013 Task 2: Sentiment Analysis in Twitter , 2013, *SEMEVAL.

[18]  Computational Model of Cognitive Development: Filtering Ambient Speech to Facilitate Word Learning , 2008 .

[19]  Chris Sinha,et al.  Symbol Grounding or the Emergence of Symbols? Vocabulary Growth in Children and a Connectionist Net , 1992 .

[20]  Alexandros Potamianos,et al.  Valence, arousal and dominance estimation for English, German, Greek, Portuguese and Spanish lexica using semantic models , 2015, INTERSPEECH.

[21]  Ping Li,et al.  Dynamic Self-Organization and Early Lexical Development in Children , 2007, Cogn. Sci..

[22]  M. Bradley,et al.  Affective Norms for English Words (ANEW): Instruction Manual and Affective Ratings , 1999 .

[23]  Gregory Grefenstette,et al.  Explorations in automatic thesaurus discovery , 1994 .

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

[25]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[26]  Chen Yu,et al.  The Role of Embodied Intention in Early Lexical Acquisition , 2005, Cogn. Sci..

[27]  Shrikanth S. Narayanan,et al.  Distributional Semantic Models for Affective Text Analysis , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[28]  R. Sánchez-Casas,et al.  Affective priming in a lexical decision task: Is there an effect of words' concreteness? , 2014 .

[29]  J. Siskind.  A computational study of cross-situational techniques for learning word-to-meaning mappings , 1996, Cognition.

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

[31]  Georgiana Dinu,et al.  Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors , 2014, ACL.

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

[33]  F. J. Pelletier.  The Principle of Semantic Compositionality , 1994 .

[34]  L. Gleitman,et al.  Propose but verify: Fast mapping meets cross-situational word learning , 2013, Cognitive Psychology.

[35]  Stephen Clark,et al.  Multi- and Cross-Modal Semantics Beyond Vision: Grounding in Auditory Perception , 2015, EMNLP.

[36]  Geoffrey E. Hinton,et al.  Zero-shot Learning with Semantic Output Codes , 2009, NIPS.

[37]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[38]  Alexandros Potamianos,et al.  Feeling is Understanding: From Affective to Semantic Spaces , 2015, IWCS.

[39]  T. McNamara.  Semantic Priming: Perspectives from Memory and Word Recognition , 2005 .

[40]  Linda B. Smith,et al.  Object perception and object naming in early development , 1998, Trends in Cognitive Sciences.