Natural language generation systems (NLG) map non-linguistic representations into strings of words through a number of steps using intermediate representations of various levels of abstraction. Template based systems, by contrast, tend to use only one representation level, i.e. fixed strings, which are combined, possibly in a sophisticated way, to generate the final text. In some circumstances, it may be profitable to combine NLG and template based techniques. The issue of combining generation techniques can be seen in more abstract terms as the issue of mixing levels of representation of different degrees of linguistic abstraction. This paper aims at defining a reference architecture for systems using mixed representations. We argue that mixed representations can be used without abandoning a linguistically grounded approach to language generation.
Mixing Representation levels: the Hybrid Approach to Automatic Text Generation
Pianta, Emanuele;
1999-01-01
Abstract
Natural language generation systems (NLG) map non-linguistic representations into strings of words through a number of steps using intermediate representations of various levels of abstraction. Template based systems, by contrast, tend to use only one representation level, i.e. fixed strings, which are combined, possibly in a sophisticated way, to generate the final text. In some circumstances, it may be profitable to combine NLG and template based techniques. The issue of combining generation techniques can be seen in more abstract terms as the issue of mixing levels of representation of different degrees of linguistic abstraction. This paper aims at defining a reference architecture for systems using mixed representations. We argue that mixed representations can be used without abandoning a linguistically grounded approach to language generation.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
