Most of the proposed algorithms concentrate on neighboring concepts (events), like "enter restaurant" --> "wait for waiter", but I have trouble finding papers on generating / retrieving longer scripts (I am not talking about narrative cloze task) which are evaluated for commonness.
Sreenivasa Rao Annaluri, sorry if I wasn't clear, my question is about text-mining and text generating approaches (if there are any other, I'd like to know!). I am looking for the most successful in generating longer scripts.
Rafal,
I have found several sources for my research under the heading of computational creativity but they are for the most part very specific to the task at hand. If you narrow down the scope towards a particular application maybe it fits some of the references that I have found.
Regards
Arturo Geigel , thank you for the suggestion. I've been working on computational creativity for some time, but the problem is that e.g. poetry (less in case of humor) allow too much freedom, whereas commonsense behavior patterns (even if unlimited in quantity) are stricter and shared by most of people which makes them hard to generate, especially because they are not expressed in one chunk of text, they must be "glued together" from pieceses scattered in various texts. My guess is that before creating something original, you need to know what is common (and boring in a sense).
- Badges
- Science topic