Summary of the paper
| Title | SINotas: the Evaluation of a NLG Application |
|---|---|
| Authors | Roberto P. A. Araujo, Rafael L. de Oliveira, Eder M. de Novais, Thiago D. Tadeu, Daniel B. Pereira and Ivandré Paraboni |
| Abstract | SINotas is a data-to-text NLG application intended to produce short textualreports on students’ academic performance from a database conveying theirgrades, weekly attendance rates and related academic information. Althoughdeveloped primarily as a testbed for Portuguese Natural Language Generation,SINotas generates reports of interest to both students keen to learn how theirprofessors would describe their efforts, and to the professors themselves, whomay benefit from an at-a-glance view of the student’s performance. In atraditional machine learning approach, SINotas uses a data-text aligned corpusas training data for decision-tree induction. The current system comprises aseries of classifiers that implement major Document Planning subtasks (namely,data interpretation, content selection, within- and between-sentencestructuring), and a small surface realisation grammar of Brazilian Portuguese.In this paper we focus on the evaluation work of the system, applying a numberof intrinsic and user-based evaluation metrics to a collection of text reportsgenerated from real application data. |
| Language | Usability, user satisfaction |
| Topics | Natural Language Generation, Tools, systems, applications, Usability, user satisfaction |
Full paper  |
SINotas: the Evaluation of a NLG Application |
| Bibtex | @InProceedings{ARAUJO10.593, author = {Roberto P. A. Araujo, Rafael L. de Oliveira, Eder M. de Novais, Thiago D. Tadeu, Daniel B. Pereira and Ivandré Paraboni}, title = {SINotas: the Evaluation of a NLG Application}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |