Statements (28)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
benchmark dataset
|
| gptkbp:citation |
Mostafazadeh et al., 2016, NAACL
|
| gptkbp:createdBy |
gptkb:Allen_Institute_for_Artificial_Intelligence
|
| gptkbp:describes |
Given a four-sentence story context and two possible endings, select the correct ending.
|
| gptkbp:field |
gptkb:machine_learning
natural language processing |
| gptkbp:format |
gptkb:text
|
| gptkbp:hasVersion |
2016 version
2018 version |
| https://www.w3.org/2000/01/rdf-schema#label |
Story Cloze Test
|
| gptkbp:introducedIn |
2016
|
| gptkbp:language |
English
|
| gptkbp:license |
free for research use
|
| gptkbp:memiliki_tugas |
multiple choice
|
| gptkbp:numberOfBooks |
1871 (test set)
|
| gptkbp:partOf |
ROCStories corpus
|
| gptkbp:purpose |
commonsense reasoning
story understanding |
| gptkbp:relatedTo |
gptkb:Winograd_Schema_Challenge
ROCStories |
| gptkbp:usedFor |
evaluating language models
evaluating narrative understanding evaluating story comprehension |
| gptkbp:usedIn |
research on commonsense reasoning
story generation evaluation |
| gptkbp:website |
https://cs.rochester.edu/nlp/rocstories/
|
| gptkbp:bfsParent |
gptkb:Commonsense_reasoning_systems
|
| gptkbp:bfsLayer |
7
|