Computer Science – Computation and Language
Scientific paper
1999-07-16
Proceedings of the AISB'99 Workshop on ``Reference Architectures and Data Standards for NLP'', Edinburgh Scotland, April 1999,
Computer Science
Computation and Language
6 pages
Scientific paper
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.
Pianta Emanuele
Tovena Lucia M.
No associations
LandOfFree
Mixing representation levels: The hybrid approach to automatic text generation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Mixing representation levels: The hybrid approach to automatic text generation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Mixing representation levels: The hybrid approach to automatic text generation will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-162638