Identification of Function Points in Software Specifications Using Natural Language Processing

Function Point Analysis is a complex task and identifying function points in a early stage specification document is the most complex part of it. Although it has been in practice for quite sometime, very little research exists regarding automating Function Point Identification and to our knowledge, none exist regarding the use of Natural Language Processing (NLP) for Function Point Analysis. In this day and age, when software development is considered to be a primary human activity, the necessity of a fully automated Function Point analysis is not disputed. We are presenting this work with the objective of establishing a platform for automated Function Point Identification based on Natural Language Processing. In particular, we have presented the details of the development of a corpus for research for Function Point Identification in specification documents. We also presented experimental results obtained using the corpus that can be useful to develop new methods to approach the problem in an objective and reproducible manner. This research and its contributions are expected to lay the foundation stone for the elaborate research on fully automatic Function Point Analysis from Natural Language specification documents.

Auteur de la thèse

Munshi Asadullah

Date de soutenance

Lundi 28 septembre 2015 à 14h

Jury

  • Pascalle Sébillot, Rapporteur
  • Yannick Toussaint, Rapporteur
  • Sophie Rosset, Examinateur
  • François Marmier, Examinateur
  • Anne Vilnat, Directeur de thèse
  • Patrick Paroubek, Co-encadrant

Publications

  • P. Paroubek, M. Asadullah, D. Nouvel, Using verb-noun patterns to detect process inputs, 17th International Conference on Text, Speech and Dialogue, Brno, Czech Republic, 08/09/2014, 181-188
  • M. Asadullah, P. Paroubek, A. Vilnat, Bidirectionnal converter between syntactic annotations : from French Treebank Dependencies to PASSAGE annotations, and back, 9th International Conference on Language Resources and Evaluation (LREC 2014), Reykjavik, Iceland, 26/05 au 31/05, 2014, 2342-2347
  • P. Paroubek, M. Asadullah, A. Vilnat, Convertir des analyses syntaxiques en dépendances vers les relations fonctionnelles PASSAGE, 20ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2013), Les Sables d'Olonne, France, 17/06 au 21/06, 2013, 675-682
  • M. Asadullah, A. Vilnat, P. Paroubek, Converting from the French Treebank Dependencies into PASSAGE syntactic annotations, 6th Language & Technology Conference : Human Language Technologies as a Challenge for Computer Science and Linguistics (L&TC 2013), Poznań, Pologne, 7/12 au 9/12, 2013, 188-182

LIMSI
Campus universitaire bât 508
Rue John von Neumann
F - 91405 Orsay cedex
Tél +33 (0) 1 69 15 80 15
Email

RAPPORTS SCIENTIFIQUES

Le LIMSI en chiffres

10 équipes de recherche
100 chercheurs et enseignants-chercheurs
40 ingénieurs et techniciens
60 doctorants
70 stagiaires

 Université Paris-Sud nouvelle fenêtre

 

Paris-Saclay nouvelle fenêtre