Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288262058> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4288262058 abstract "The recent success of natural language understanding (NLU) systems has been troubled by results highlighting the failure of these models to generalize in a systematic and robust way. In this work, we introduce a diagnostic benchmark suite, named CLUTRR, to clarify some key issues related to the robustness and systematicity of NLU systems. Motivated by classic work on inductive logic programming, CLUTRR requires that an NLU system infer kinship relations between characters in short stories. Successful performance on this task requires both extracting relationships between entities, as well as inferring the logical rules governing these relationships. CLUTRR allows us to precisely measure a model's ability for systematic generalization by evaluating on held-out combinations of logical rules, and it allows us to evaluate a model's robustness by adding curated noise facts. Our empirical results highlight a substantial performance gap between state-of-the-art NLU models (e.g., BERT and MAC) and a graph neural network model that works directly with symbolic inputs---with the graph-based model exhibiting both stronger generalization and greater robustness." @default.
- W4288262058 created "2022-07-28" @default.
- W4288262058 creator A5004542284 @default.
- W4288262058 creator A5019642748 @default.
- W4288262058 creator A5052862844 @default.
- W4288262058 creator A5080591144 @default.
- W4288262058 creator A5085067496 @default.
- W4288262058 date "2019-08-16" @default.
- W4288262058 modified "2023-10-16" @default.
- W4288262058 title "CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text" @default.
- W4288262058 doi "https://doi.org/10.48550/arxiv.1908.06177" @default.
- W4288262058 hasPublicationYear "2019" @default.
- W4288262058 type Work @default.
- W4288262058 citedByCount "0" @default.
- W4288262058 crossrefType "posted-content" @default.
- W4288262058 hasAuthorship W4288262058A5004542284 @default.
- W4288262058 hasAuthorship W4288262058A5019642748 @default.
- W4288262058 hasAuthorship W4288262058A5052862844 @default.
- W4288262058 hasAuthorship W4288262058A5080591144 @default.
- W4288262058 hasAuthorship W4288262058A5085067496 @default.
- W4288262058 hasBestOaLocation W42882620581 @default.
- W4288262058 hasConcept C104317684 @default.
- W4288262058 hasConcept C119857082 @default.
- W4288262058 hasConcept C13280743 @default.
- W4288262058 hasConcept C134306372 @default.
- W4288262058 hasConcept C154945302 @default.
- W4288262058 hasConcept C166957645 @default.
- W4288262058 hasConcept C177148314 @default.
- W4288262058 hasConcept C185592680 @default.
- W4288262058 hasConcept C185798385 @default.
- W4288262058 hasConcept C195324797 @default.
- W4288262058 hasConcept C204321447 @default.
- W4288262058 hasConcept C205649164 @default.
- W4288262058 hasConcept C2779382394 @default.
- W4288262058 hasConcept C2779439875 @default.
- W4288262058 hasConcept C33923547 @default.
- W4288262058 hasConcept C41008148 @default.
- W4288262058 hasConcept C55493867 @default.
- W4288262058 hasConcept C63479239 @default.
- W4288262058 hasConcept C79581498 @default.
- W4288262058 hasConcept C80444323 @default.
- W4288262058 hasConcept C95457728 @default.
- W4288262058 hasConceptScore W4288262058C104317684 @default.
- W4288262058 hasConceptScore W4288262058C119857082 @default.
- W4288262058 hasConceptScore W4288262058C13280743 @default.
- W4288262058 hasConceptScore W4288262058C134306372 @default.
- W4288262058 hasConceptScore W4288262058C154945302 @default.
- W4288262058 hasConceptScore W4288262058C166957645 @default.
- W4288262058 hasConceptScore W4288262058C177148314 @default.
- W4288262058 hasConceptScore W4288262058C185592680 @default.
- W4288262058 hasConceptScore W4288262058C185798385 @default.
- W4288262058 hasConceptScore W4288262058C195324797 @default.
- W4288262058 hasConceptScore W4288262058C204321447 @default.
- W4288262058 hasConceptScore W4288262058C205649164 @default.
- W4288262058 hasConceptScore W4288262058C2779382394 @default.
- W4288262058 hasConceptScore W4288262058C2779439875 @default.
- W4288262058 hasConceptScore W4288262058C33923547 @default.
- W4288262058 hasConceptScore W4288262058C41008148 @default.
- W4288262058 hasConceptScore W4288262058C55493867 @default.
- W4288262058 hasConceptScore W4288262058C63479239 @default.
- W4288262058 hasConceptScore W4288262058C79581498 @default.
- W4288262058 hasConceptScore W4288262058C80444323 @default.
- W4288262058 hasConceptScore W4288262058C95457728 @default.
- W4288262058 hasLocation W42882620581 @default.
- W4288262058 hasOpenAccess W4288262058 @default.
- W4288262058 hasPrimaryLocation W42882620581 @default.
- W4288262058 hasRelatedWork W1485630101 @default.
- W4288262058 hasRelatedWork W1549839673 @default.
- W4288262058 hasRelatedWork W1596426534 @default.
- W4288262058 hasRelatedWork W172995687 @default.
- W4288262058 hasRelatedWork W2128387655 @default.
- W4288262058 hasRelatedWork W2968398601 @default.
- W4288262058 hasRelatedWork W2971107062 @default.
- W4288262058 hasRelatedWork W2972987451 @default.
- W4288262058 hasRelatedWork W2978467928 @default.
- W4288262058 hasRelatedWork W3084863322 @default.
- W4288262058 isParatext "false" @default.
- W4288262058 isRetracted "false" @default.
- W4288262058 workType "article" @default.