Mining commonalities and variabilities from natural language documents

A company who wishes to enter an established marked with a new, competitive product is required to analyse the product solutions of the competitors. Identifying and comparing the features provided by the other vendors might greatly help during the market analysis. However, mining common and variant features of from the publicly available documents of the competitors is a time consuming and error-prone task. In this paper, we suggest to employ a natural language processing approach based on contrastive analysis to identify commonalities and variabilities from the brochures of a group of vendors. We present a first step towards a practical application of the approach, in the the context of the market of Communications-Based Train Control (CBTC) systems.

[1]  Nan Niu,et al.  Extracting and Modeling Product Line Functional Requirements , 2008, 2008 16th IEEE International Requirements Engineering Conference.

[2]  Simonetta Montemagni,et al.  A Contrastive Approach to Multi-word Extraction from Domain-specific Corpora , 2010, LREC.

[3]  Nan Niu,et al.  On-Demand Cluster Analysis for Product Line Functional Requirements , 2008, 2008 12th International Software Product Line Conference.

[4]  Ruzanna Chitchyan,et al.  A framework for constructing semantically composable feature models from natural language requirements , 2009, SPLC.

[5]  Felice Dell'Orletta,et al.  Ensemble system for Part-of-Speech tagging , 2009 .

[6]  Isabel John,et al.  Capturing Product Line Information from Legacy User Documentation , 2006, Software Product Lines.

[7]  Kyo Chul Kang,et al.  Feature-Oriented Domain Analysis (FODA) Feasibility Study , 1990 .

[8]  Mathieu Acher,et al.  On extracting feature models from product descriptions , 2012, VaMoS.

[9]  Christoph Pohl,et al.  An Exploratory Study of Information Retrieval Techniques in Domain Analysis , 2008, 2008 12th International Software Product Line Conference.

[10]  Krzysztof Czarnecki,et al.  Reverse engineering feature models , 2011, 2011 33rd International Conference on Software Engineering (ICSE).

[11]  Alessio Ferrari,et al.  Product Line Engineering Applied to CBTC Systems Development , 2012, ISoLA.

[12]  Rubén Prieto-Díaz,et al.  DARE: Domain analysis and reuse environment , 1998, Ann. Softw. Eng..

[13]  Jane Cleland-Huang,et al.  On-demand feature recommendations derived from mining public product descriptions , 2011, 2011 33rd International Conference on Software Engineering (ICSE).

[14]  Haiyan Zhao,et al.  An approach to constructing feature models based on requirements clustering , 2005, 13th IEEE International Conference on Requirements Engineering (RE'05).