From neural activation to symbolic alignment: A network-based approach to the formation of dialogue lexica

We present a lexical network model, called TiTAN, that captures the formation and the structure of natural language dialogue lexica. The model creates a bridge between neural connectionist networks and symbolic architectures: On the one hand, TiTAN is driven by the neural motor of lexical alignment, namely priming. On the other hand, TiTAN accounts for observed symbolic output of interlocutors, namely uttered words. The TiTAN series update is driven by the dialogue inherent dynamics of turns and incorporates a measure of the structural similarity of graphs. This allows to apply and evaluate the model: TiTAN is tested classifying 55 experimental dialogue data according to their alignment status. The trade-off between precision and recall of the classification results in an F-score of 0.92.

[1]  Miro Kraetzl,et al.  Graph distances using graph union , 2001, Pattern Recognit. Lett..

[2]  Alexander Mehler,et al.  Taking Fingerprints of Speech-And-Gesture Ensembles. Approaching Empirical Evidence of Intrapersonal Alignment in Multimodal Communication , 2008 .

[3]  Alexandra A. Cleland,et al.  Syntactic co-ordination in dialogue , 2000, Cognition.

[4]  Petra Weiß,et al.  Coordination in dialog: Alignment of object naming in the Jigsaw Map Game , 2008 .

[5]  Matthias Dehmer,et al.  Information processing in complex networks: Graph entropy and information functionals , 2008, Appl. Math. Comput..

[6]  Alexander Kraskov,et al.  MIC: Mutual Information Based Hierarchical Clustering , 2008, 0809.1605.

[7]  J. H. Neely.  Semantic priming and retrieval from lexical memory: Roles of inhibitionless spreading activation and limited-capacity attention. , 1977 .

[8]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[9]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[10]  Petra Weiß,et al.  A Network Model of Interpersonal Alignment in Dialog , 2010, Entropy.

[11]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[12]  Hans-Jürgen Eikmeyer,et al.  Alignment und Ontologien , 2007, GI Jahrestagung.

[13]  Alessandro Vespignani,et al.  The Architecture of Complex Weighted Networks: Measurements and Models , 2007 .

[14]  Guido E. Vallejos.  Mindware: An introduction to the philosophy of cognitive science , 2010 .

[15]  Petra Weiß,et al.  TOWARDS A SIMULATION MODEL OF DIALOGICAL ALIGNMENT , 2010 .

[16]  Gert Rickheit,et al.  Alignment und Aushandlung im Dialog , 2005 .

[17]  Alexander Mehler,et al.  Assessing Lexical Alignment in Spontaneous Direction Dialogue Data by Means of a Lexicon Network Model , 2011, CICLing.

[18]  Martin J. Pickering,et al.  An empirical investigation into spatial reference frame taxonomy using dialogue. , 2006 .

[19]  H. H. Clark,et al.  Referring as a collaborative process , 1986, Cognition.

[20]  Mark E. J. Newman,et al.  The Structure and Function of Complex Networks , 2003, SIAM Rev..

[21]  V. Ferreira,et al.  The functions of structural priming , 2006, Language and cognitive processes.

[22]  Olga Pustylnikov,et al.  Patterns of alignment in dialogue: Conversational partners do not always stay aligned on common object names , 2009 .

[23]  Zenzi M. Griffin,et al.  The persistence of structural priming: transient activation or implicit learning? , 2000, Journal of experimental psychology. General.

[24]  Massimo Poesio,et al.  Completions, Coordination, and Alignment in Dialogue , 2010, Dialogue Discourse.

[25]  M. Pickering,et al.  Toward a mechanistic psychology of dialogue , 2004, Behavioral and Brain Sciences.

[26]  Alexander Mehler,et al.  STRUCTURAL SIMILARITIES OF COMPLEX NETWORKS: A COMPUTATIONAL MODEL BY EXAMPLE OF WIKI GRAPHS , 2008, Appl. Artif. Intell..

[27]  H. Giles,et al.  Speech style and social evaluation , 1975 .

[28]  David E. Rumelhart,et al.  Introduction to human information processing , 1977 .

[29]  Alexander Mehler,et al.  A structural model of semiotic alignment: The classification of multimodal ensembles as a novel machine learning task , 2009, AFRICON 2009.

[30]  V. Yngve.  On getting a word in edgewise , 1970 .

[31]  S. Garrod,et al.  Saying what you mean in dialogue: A study in conceptual and semantic co-ordination , 1987, Cognition.

[32]  Robert Stalnaker,et al.  Common Ground , 2002 .

[33]  Ben Shneiderman,et al.  Structural analysis of hypertexts: identifying hierarchies and useful metrics , 1992, TOIS.

[34]  Andrew J. Stewart,et al.  Syntactic priming in spoken production: Linguistic and temporal interference , 2000, Memory & cognition.

[35]  Stefan Kopp,et al.  Data-based analysis of speech and gesture: the Bielefeld Speech and Gesture Alignment corpus (SaGA) and its applications , 2013, Journal on Multimodal User Interfaces.

[36]  M E J Newman,et al.  Finding and evaluating community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.