Our accent detection algorithm proves to be very robust. The primary failure of our filter is on the detection of “non-standard” rhymes, which we highlight as an outstanding challenge in computational poetics. More precisely, we produce an algorithm which focuses on the structural aspects of the limerick – rhyme scheme and rhythm (i.e., stress patterns) – and when tested on a a culled data set of 98,454 publicly available limericks, our “limerick filter” accepts 67% as limericks. This turns out to be a surprisingly difficult challenge with many subtleties. Abstract In this paper we take up the problem of “limerick detection” and describe a system to identify five-line poems as limericks or not.
0 Comments
Leave a Reply. |