Abstract | ||
---|---|---|
Incongruity resolution is one of the most widely accepted theories of humour, suggesting that humour is due to the mixing of two disparate interpretation frames in one statement. In this paper, we explore several computational models for incongruity resolution. We introduce a new data set, consisting of a series of ‘set-ups' (preparations for a punch line), each of them followed by four possible coherent continuations out of which only one has a comic effect. Using this data set, we redefine the task as the automatic identification of the humorous punch line among all the plausible endings. We explore several measures of semantic relatedness, along with a number of joke-specific features, and try to understand their appropriateness as computational models for incongruity detection. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-12116-6_30 | CICLing |
Keywords | Field | DocType |
accepted theory,incongruity resolution,punch line,automatic identification,comic effect,new data,incongruity detection,computational model,humorous punch line,computer model,sentiment analysis,semantic relatedness | Semantic similarity,Singular value decomposition,Comics,Computer science,Sentiment analysis,Computational model,Natural language processing,Artificial intelligence,Latent semantic analysis,Word-sense disambiguation | Conference |
Volume | ISSN | ISBN |
6008 | 0302-9743 | 3-642-12115-2 |
Citations | PageRank | References |
13 | 0.94 | 14 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rada Mihalcea | 1 | 6460 | 445.54 |
Carlo Strapparava | 2 | 2564 | 230.59 |
Stephen Pulman | 3 | 450 | 38.31 |