2010
DOI: 10.1007/s11023-010-9209-8
|View full text |Cite
|
Sign up to set email alerts
|

Assessing the Novelty of Computer-Generated Narratives Using Empirical Metrics

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
13
0

Year Published

2012
2012
2022
2022

Publication Types

Select...
6
1
1

Relationship

1
7

Authors

Journals

citations
Cited by 14 publications
(13 citation statements)
references
References 7 publications
0
13
0
Order By: Relevance
“…Novelty testing follows the general procedure outlined in Peinado et al, 2010, [11] This procedure for novelty testing was intended to numerically determine a story's novelty by computing the distance between two different stories. The concept behind novelty testing is to determine how different Story A is from Story B by analyzing several different elements of each story.…”
Section: Novelty Testingmentioning
confidence: 99%
See 2 more Smart Citations
“…Novelty testing follows the general procedure outlined in Peinado et al, 2010, [11] This procedure for novelty testing was intended to numerically determine a story's novelty by computing the distance between two different stories. The concept behind novelty testing is to determine how different Story A is from Story B by analyzing several different elements of each story.…”
Section: Novelty Testingmentioning
confidence: 99%
“…The weighting of the system helped to determine how novel the new story was from the original well-known tale. Peinado et al [11] used the following equations to calculate the event element.…”
Section: Novelty Testingmentioning
confidence: 99%
See 1 more Smart Citation
“…Outputs will be rated automatically on the following parameters: grammaticality -based on conformance to the grammar -, novelty with respect to reference stories in the source materials -data structures built by the parser from the outputs will be compared with those arising from the reference stories according to existing metrics for narrative similarity (Peinado et al, 2010;Hervás et al, 2015) -, and additional rating schemes developed for any relevant features -as the data structures generated by the parser will include explicit representation of these aspects, development for specif metrics is possible for features like degree of causal connectivity, rise and fall of emotion or affinity between characters over a story, or any others explicitly represented.…”
Section: Evaluation Proceduresmentioning
confidence: 99%
“…Each of Rowe et al 1 and Zhu 2 presented multiple viewpoints to evaluate narrative generation system including the authorial process or intention, generated texts, and process or modes of reading. Each of Pérez y Pérez 3 and Peinado et al 4 presented formalization of such evaluation criteria as coherence, interestingness, and novelty in generated narratives.…”
Section: Introductionmentioning
confidence: 99%