Empirically-based Control of Natural Language Generation

In this paper we present a new approach to controlling the behaviour of a natural language generation system by correlating internal decisions taken during free generation of a wide range of texts with the surface stylistic characteristics of the resulting outputs, and using the correlation to control the generator. This contrasts with the generate-and-test architecture adopted by most previous empirically-based generation approaches, offering a more efficient, generic and holistic method of generator control. We illustrate the approach by describing a system in which stylistic variation (in the sense of Biber (1988)) can be effectively controlled during the generation of short medical information texts.

[1]  Wolfgang Hoeppner,et al.  Review of Generating natural language under pragmantic constraints by Edward H. Hovy. Lawrence Erlbaum Associates 1988. , 1990 .

[2]  S. Weisberg.  Applied Linear Regression, 2nd Edition. , 1987 .

[3]  Eduard Hovy,et al.  Generating Natural Language Under Pragmatic Constraints , 1988 .

[4]  Daniel S. Paiva.  Investigating style in a corpus of pharmaceutical leaflets : results of a factor analysis , 2000 .

[5]  Scott Weinstein,et al.  Centering: A Framework for Modeling the Local Coherence of Discourse , 1995, CL.

[6]  Marilyn A. Walker,et al.  Training a sentence planner for spoken dialogue using boosting , 2002, Comput. Speech Lang..

[7]  David J. Weir,et al.  Engineering a Wide-Coverage Lexicalized Grammar , 2000, TAG+.

[8]  Daniel S. Paiva.  Using stylistic parameters to control a natural language generation system , 2004 .

[9]  Robert Sigley,et al.  Text categories and where you can stick them : A crude formality index , 1997 .

[10]  Nicolas N. Nicolov,et al.  Approximate text generation from non-hierarchical representations in a declarative framework , 1999 .

[11]  Irene Langkilde-Geary,et al.  An Empirical Verification of Coverage and Correctness for a General-Purpose Sentence Generator , 2002, INLG.

[12]  Kathleen McKeown,et al.  Text generation: using discourse strategies and focus constraints to generate natural language text , 1985 .

[13]  Douglas Biber,et al.  Variation across speech and writing: Methodology , 1988 .

[14]  Roger Evans,et al.  A Framework for Stylistically Controlled Generation , 2004, INLG.

[15]  Kees van Deemter,et al.  From RAGS to RICHES: Exploiting the Potential of a Flexible Generation Architecture , 2001, ACL.

[16]  Chrysanne Di Marco,et al.  Stylistic Decision-Making in Natural Language Generation , 1993, EWNLG.