Model-driven adaptation of question answering systems for ambient intelligence by integrating restricted-domain knowledge

Ambient Intelligence (AmI) requires Question Answering (QA) systems for providing intuitive interfaces to state natural language questions and obtaining precise answers related to some specific topic. Therefore, adapting QA systems to new restricted domains is an increasingly necessity for these systems to be applied in AmI environments. Unfortunately, research addressing adaptation of QA systems to new domains has two main drawbacks: (i) QA systems are manually tuned, which requires a huge effort in time and cost, and (ii) tuning of QA systems depends on the specific representation scheme of the restricted-domain knowledge, thus hinders incorporation of new resources into the system. To overcome these drawbacks, this paper presents a novel approach based on model-driven development in order to seamlessly integrate textual information and knowledge resources to automatically and effortlessly adapt QA systems to be useful for restricted-domain AmI environments, such as e-Science.

[1]  Juan Carlos Augusto,et al.  Ambient Intelligence—the Next Step for Artificial Intelligence , 2008, IEEE Intelligent Systems.

[2]  James A. Hendler,et al.  Guest Editors' Introduction: E-Science , 2004, IEEE Intelligent Systems.

[3]  Sergio Ferrández,et al.  Investigating the Best Configuration of HMM Spanish PoS Tagger when Minimum Amount of Training Data Is Available , 2005, NLDB.

[4]  Manuel Palomar,et al.  An Empirical Approach to Spanish Anaphora Resolution , 1999, Machine Translation.

[5]  Leila Kosseim,et al.  Improving the performance of question answering with semantically equivalent answer patterns , 2008, Data Knowl. Eng..

[6]  Daniel Ferrés,et al.  Experiments Adapting an Open-Domain Question Answering System to the Geographical Domain Using Scope-Based Resources , 2006 .

[7]  Gail Hodge,et al.  Systems of Knowledge Organization for Digital Libraries: Beyond Traditional Authority Files , 2000 .

[8]  Ulf Hermjakob,et al.  Parsing and Question Classification for Question Answering , 2001, ACL 2001.

[9]  Nicholas R. Jennings,et al.  The Semantic Grid: Past, Present, and Future , 2005 .

[10]  Anneke Kleppe,et al.  MDA explained - the Model Driven Architecture: practice and promise , 2003, Addison Wesley object technology series.

[11]  Jean Bézivin,et al.  On the unification power of models , 2005, Software & Systems Modeling.

[12]  Antonio Ferrández Rodríguez,et al.  Using AliQAn in Monolingual QA@CLEF 2008 , 2008, CLEF.

[13]  Eduard H. Hovy,et al.  Learning surface text patterns for a Question Answering System , 2002, ACL.

[14]  Diego Molla Aliod,et al.  Question Answering in Restricted Domains: An Overview , 2007, CL.

[15]  Carlos Ramos,et al.  Ambient Intelligence - A State of the Art from Artificial Intelligence Perspective , 2007, EPIA Workshops.

[16]  Bran Selic,et al.  The Pragmatics of Model-Driven Development , 2003, IEEE Softw..

[17]  Jose-Norberto Mazón,et al.  Model-Driven Knowledge-Based Development of Expected Answer Type Taxonomies for Restricted Domain Question Answering , 2010, MTSR.

[18]  Anselmo Peñas,et al.  Overview of ResPubliQA 2009: Question Answering Evaluation over European Legislation , 2009, CLEF.

[19]  Max Mühlhäuser,et al.  Natural Language Processing for Ambient Intelligence , 2007, Künstliche Intell..

[20]  David De Roure.  e-Science and the Web , 2010, Computer.

[21]  Sanda M. Harabagiu,et al.  FALCON: Boosting Knowledge for Answer Engines , 2000, TREC.