The Sentence Fairy: a natural-language generation system to support children's essay writing

We built an NLP system implementing a ‘virtual writing conference’ for elementary-school children, with German as the target language. Currently, state-of-the-art computer support for writing tasks is restricted to multiple-choice questions or quizzes because automatic parsing of the often ambiguous and fragmentary texts produced by pupils presents insurmountable problems. Here, we follow a different course by deploying natural language generation technology to evaluate and improve the grammatical quality of student output. Based on an abstract representation of the story under construction, all paraphrases of simple and combined clauses are generated fully automatically. From this source, the system produces exercises enabling the pupils to improve their sentences. We apply parsing technology only in the teacher mode, where new stories are entered into the system in a simple manner. The system we describe here is a prototype including a full exercise generation mode and a rudimentary teacher mode.

[1]  John A. Bateman,et al.  Enabling technology for multilingual natural language generation: the KPML development environment , 1997, Natural Language Engineering.

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

[3]  Mariët Theune,et al.  The Narrator: NLG for digital storytelling , 2007, ENLG.

[4]  John Nerbonne,et al.  Morphological Processing and Computer-Assisted Language Learning , 1998 .

[5]  Sylviane Granger,et al.  Computer learner corpus research: current status and future prospects , 2004 .

[6]  Karin Harbusch,et al.  Interactive sentence combining and paraphrasing in support of integrated writing and grammar instruction: A new application area for natural language sentence generators , 2007, ENLG.

[7]  Ewan Klein,et al.  Natural Language Processing with Python , 2009 .

[8]  Pam Altman,et al.  Sentence-Combining Workbook , 2000 .

[9]  William C. Mann,et al.  Rhetorical Structure Theory: Toward a functional theory of text organization , 1988 .

[10]  James C. Lester,et al.  Narrative prose generation , 2001, Artif. Intell..

[11]  Michael Zock,et al.  Converting an electronic dictionary into a drill tutor , 2004 .

[12]  Karin Harbusch,et al.  6. Dutch and German verb constructions in Performance Grammar , 2003 .

[13]  Martin Forst,et al.  An LFG Grammar Checker for CALL , 2004 .

[14]  Jill Burstein,et al.  Automated Essay Scoring : A Cross-disciplinary Perspective , 2003 .

[15]  Karin Harbusch,et al.  A Quantitative Model of Word Order and Movement in English, Dutch and German Complement Constructions , 2002, COLING.

[16]  Juan Rafael Zamorano-Mansilla,et al.  Text generators , error analysis and feedback , 2004 .

[17]  Karin Harbusch,et al.  Performance Grammar: a Declarative Definition , 2001, CLIN.

[18]  U. Felix E-learning pedagogy in the third millennium: the need for combining social and cognitive constructivist approaches , 2005, ReCALL.

[19]  Karin Harbusch,et al.  A Generation-Oriented Workbench for Performance Grammar: Capturing Linear Order Variability in German and Dutch , 2006, INLG.

[20]  Trude Heift,et al.  Error Diagnosis and Error Correction in CALL. , 2003 .

[21]  Dan Flickinger,et al.  Minimal Recursion Semantics: An Introduction , 2005 .

[22]  Sebastien L'Haire,et al.  Error Diagnosis in the FreeText Project , 2003 .

[23]  Herbert Schildt Natural-language processing in C , 1987 .

[24]  Caroline Fränkel Evaluation von Syntaxanalysemethoden angewendet auf Datenmaterial aus transliterierten Schulaufsätzen , 2008 .

[25]  Robert Dale,et al.  Building applied natural language generation systems , 1997, Natural Language Engineering.

[26]  Donald A. Daiker Sentence Combining: A Rhetorical Perspective. , 1987 .

[27]  Robert Dale,et al.  Building Natural Language Generation Systems: Figures , 2000 .

[28]  John C. Mellon Transformational Sentence Combining: A Method for Enhancing the Development of Syntactic Fluency in English Composition , 1969 .