In the following, we use the term automated text generation [23] to refer to both template-based and linguistically motivated generation methods.
Template-based generation methods require only a partial representation of the content to be conveyed. Furthermore, this method can be easily integrated into application programs; only little linguistic knowledge is required. On the other hand, as large portions of text are fixed within templates, the texts produced with this method tend to be monotonic and the activation of the same templates with different values for template variables results in repetitive sentences structures.
The large number of templates required for a flexible or multilingual realization of figure captions is a further disadvantage of the template-based generation method.
Linguistically motivated generation methods are appropriate for the generation of flexible text, as these methods concentrate on the generation of coherent and cohesive texts using a large variety of syntactic structures. To establish cohesion in text appropriately, choices of definite descriptions (pronouns, nominal groups) and the aggregation of parallel structures are an important means. However, for these methods a formal representation (domain knowledge, user models and a representation of the context) and large linguistic resources (grammars and lexica) are necessary which leads to a high initial overhead with respect to the amount of work to be invested.