Dynamic Building of Domain Specific Lexicons Using Emergent Semantics

The majority of current Natural Language Processing (NLP) methods and research is based on statistical analysis and machine learning. While these methods are quite effective, they are not perfect and the search continues for better and more accurate methods for NLP. The work of Kleiner et al. (Kleiner et al. 2009) takes a very different approach. They look at NLP as a model transformation problem, utilising configuration as a model transformation to deal with the ambiguity of natural language. Model transformations are used heavily in Model Driven Engineering (MDE) and are the process of producing an output model, or several, from one or more input models. Configuration is a general method of constraint based searching that, in this case, is used to search for a model conforming to the desired meta-model. Although Kleiner et al. (Kleiner et al. 2009) show promising results, their method requires the use of a predefined lexicon to support the transformations from natural language to a useful model representation. This means that in order to utilise this method a complete lexicon needs to be defined for the domain it is being used for, which is quite impractical. This research aims to develop a method of dynamically building a lexicon based on a multi-agent system, and the principles of Emergent Semantics, and Semiotic Dynamics in a similar way to that described by Steels and Hanappe (Steels and Hanappe 2006). By dynamically generating a lexicon based on the input text the amount of time required to define a lexicon would be reduced, with the potential for a fully automated process. Therefore, the overall development time of software would be reduced through the automatic transformation of specifications to formal representations (such as UML class diagrams). In addition, it would make updating the lexicon simpler as it would become a natural ability of the system. Finally, the dynamic generation may have longe range benefits for research in semantic interoperability and

[1]  Joakim Nivre,et al.  Inductive Dependency Parsing , 2006, Text, speech and language technology.

[2]  George A. Miller,et al.  CYC, WordNet, and EDR: critiques and responses , 1995, CACM.

[3]  Jean Bézivin,et al.  KM3: A DSL for Metamodel Specification , 2006, FMOODS.

[4]  Jean-Marie Favre,et al.  Towards a Megamodel to Model Software Evolution Through Transformations , 2005, SETra@ICGT.

[5]  Steffen Staab,et al.  Ontology Learning for the Semantic Web , 2002, IEEE Intell. Syst..

[6]  Laurent Henocque,et al.  Parsing Languages with a Configurator , 2004, ECAI.

[7]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[8]  Mary Shaw,et al.  What makes good research in software engineering? , 2002, International Journal on Software Tools for Technology Transfer.

[9]  Luc Steels,et al.  Interoperability Through Emergent Semantics A Semiotic Dynamics Approach , 2006, J. Data Semant..

[10]  Douglas B. Lenat,et al.  CYC: a large-scale investment in knowledge infrastructure , 1995, CACM.

[11]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[12]  Toshio Yokoi,et al.  The EDR electronic dictionary , 1995, CACM.

[13]  Frank Nack.  Media information spaces - a semantic challenge , 2002 .

[14]  Walter Daelemans,et al.  Memory-Based Language Processing , 2009, Studies in natural language processing.

[15]  Steffen Staab,et al.  Emergent Semantics Principles and Issues , 2004, DASFAA.

[16]  Barbara J. Grosz,et al.  Natural-Language Processing , 1982, Artificial Intelligence.

[17]  Guido Boella,et al.  Normative framework for normative system change , 2009, AAMAS 2009.

[18]  Jianfeng Gao,et al.  A Comparative Study of Parameter Estimation Methods for Statistical Natural Language Processing , 2007, ACL.

[19]  James A. Hendler,et al.  The Semantic Web" in Scientific American , 2001 .

[20]  Shane Sendall,et al.  Model Transformation: The Heart and Soul of Model-Driven Software Development , 2003, IEEE Softw..

[21]  James H. Martin,et al.  Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, 2nd Edition , 2000, Prentice Hall series in artificial intelligence.

[22]  Alexander Maedche.  Emergent semantics for ontologies , 2002 .