Statements (61)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:psychology
|
| gptkbp:adapted_into |
gptkb:various_languages
|
| gptkbp:aims_to |
test AI systems
|
| gptkbp:challenges |
gptkb:Artificial_Intelligence
machine learning models text comprehension deep learning models language models natural language generation AI comprehension tasks AI language understanding contextual AI systems |
| gptkbp:consists_of |
pairs of sentences
|
| gptkbp:designed_to_evaluate |
natural language understanding
|
| gptkbp:developed_by |
gptkb:Ernest_Davis
gptkb:Leora_Morgenstern |
| gptkbp:enhances |
AI comprehension skills
|
| gptkbp:first_introduced |
gptkb:2014
|
| gptkbp:has_a_focus_on |
AI ethics discussions
|
| gptkbp:has_implications_for |
natural language processing
|
| https://www.w3.org/2000/01/rdf-schema#label |
Winograd Schema Challenge
|
| gptkbp:includes |
ambiguous sentences
|
| gptkbp:is_a_subject_of |
research studies
|
| gptkbp:is_a_tool_for |
research in linguistics
|
| gptkbp:is_an_indicator_of |
AI's reasoning ability
|
| gptkbp:is_based_on |
Winograd Schema
|
| gptkbp:is_considered_as |
benchmark for AI
|
| gptkbp:is_distinct_from |
multiple-choice tests
|
| gptkbp:is_evaluated_by |
human judges
|
| gptkbp:is_influenced_by |
contextual clues
linguistic ambiguity |
| gptkbp:is_often_compared_to |
gptkb:SQu_AD
|
| gptkbp:is_part_of |
gptkb:AI_technology
cognitive science AI training datasets AI evaluation metrics AI development processes |
| gptkbp:is_referenced_in |
academic papers
|
| gptkbp:is_related_to |
cognitive psychology
semantic understanding |
| gptkbp:is_similar_to |
gptkb:Turing_Test
|
| gptkbp:is_tested_for |
semantic reasoning
linguistic knowledge common sense reasoning contextual inference disambiguation skills pragmatic reasoning syntactic understanding |
| gptkbp:is_used_in |
AI competitions
|
| gptkbp:is_used_to |
measure machine comprehension
|
| gptkbp:measures |
contextual understanding
AI's ability to infer meaning AI's interpretative skills |
| gptkbp:performance |
natural language understanding tasks
|
| gptkbp:requires |
disambiguation of pronouns
|
| gptkbp:skills |
world facts
|
| gptkbp:tests_ability_to |
understand context
|
| gptkbp:was_a_response_to |
limitations of previous tests
|
| gptkbp:bfsParent |
gptkb:LLa_MA
gptkb:SHRDLU |
| gptkbp:bfsLayer |
6
|