Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378465055> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4378465055 abstract "We address the fundamental challenge in Natural Language Generation (NLG) model evaluation, the design and validation of evaluation metrics. Recognizing the limitations of existing metrics and issues with human judgment, we propose using measurement theory, the foundation of test design, as a framework for conceptualizing and evaluating the validity and reliability of NLG evaluation metrics. This approach offers a systematic method for defining good metrics, developing robust metrics, and assessing metric performance. In this paper, we introduce core concepts in measurement theory in the context of NLG evaluation and key methods to evaluate the performance of NLG metrics. Through this framework, we aim to promote the design, evaluation, and interpretation of valid and reliable metrics, ultimately contributing to the advancement of robust and effective NLG models in real-world settings." @default.
- W4378465055 created "2023-05-27" @default.
- W4378465055 creator A5017572712 @default.
- W4378465055 creator A5051199951 @default.
- W4378465055 creator A5083645580 @default.
- W4378465055 creator A5085502421 @default.
- W4378465055 date "2023-05-24" @default.
- W4378465055 modified "2023-09-25" @default.
- W4378465055 title "Evaluating NLG Evaluation Metrics: A Measurement Theory Perspective" @default.
- W4378465055 doi "https://doi.org/10.48550/arxiv.2305.14889" @default.
- W4378465055 hasPublicationYear "2023" @default.
- W4378465055 type Work @default.
- W4378465055 citedByCount "0" @default.
- W4378465055 crossrefType "posted-content" @default.
- W4378465055 hasAuthorship W4378465055A5017572712 @default.
- W4378465055 hasAuthorship W4378465055A5051199951 @default.
- W4378465055 hasAuthorship W4378465055A5083645580 @default.
- W4378465055 hasAuthorship W4378465055A5085502421 @default.
- W4378465055 hasBestOaLocation W43784650551 @default.
- W4378465055 hasConcept C119857082 @default.
- W4378465055 hasConcept C121332964 @default.
- W4378465055 hasConcept C12713177 @default.
- W4378465055 hasConcept C127413603 @default.
- W4378465055 hasConcept C151730666 @default.
- W4378465055 hasConcept C154945302 @default.
- W4378465055 hasConcept C163258240 @default.
- W4378465055 hasConcept C176217482 @default.
- W4378465055 hasConcept C195324797 @default.
- W4378465055 hasConcept C21547014 @default.
- W4378465055 hasConcept C2776187449 @default.
- W4378465055 hasConcept C2779343474 @default.
- W4378465055 hasConcept C41008148 @default.
- W4378465055 hasConcept C43214815 @default.
- W4378465055 hasConcept C539667460 @default.
- W4378465055 hasConcept C62520636 @default.
- W4378465055 hasConcept C86803240 @default.
- W4378465055 hasConceptScore W4378465055C119857082 @default.
- W4378465055 hasConceptScore W4378465055C121332964 @default.
- W4378465055 hasConceptScore W4378465055C12713177 @default.
- W4378465055 hasConceptScore W4378465055C127413603 @default.
- W4378465055 hasConceptScore W4378465055C151730666 @default.
- W4378465055 hasConceptScore W4378465055C154945302 @default.
- W4378465055 hasConceptScore W4378465055C163258240 @default.
- W4378465055 hasConceptScore W4378465055C176217482 @default.
- W4378465055 hasConceptScore W4378465055C195324797 @default.
- W4378465055 hasConceptScore W4378465055C21547014 @default.
- W4378465055 hasConceptScore W4378465055C2776187449 @default.
- W4378465055 hasConceptScore W4378465055C2779343474 @default.
- W4378465055 hasConceptScore W4378465055C41008148 @default.
- W4378465055 hasConceptScore W4378465055C43214815 @default.
- W4378465055 hasConceptScore W4378465055C539667460 @default.
- W4378465055 hasConceptScore W4378465055C62520636 @default.
- W4378465055 hasConceptScore W4378465055C86803240 @default.
- W4378465055 hasLocation W43784650551 @default.
- W4378465055 hasOpenAccess W4378465055 @default.
- W4378465055 hasPrimaryLocation W43784650551 @default.
- W4378465055 hasRelatedWork W2961085424 @default.
- W4378465055 hasRelatedWork W3046775127 @default.
- W4378465055 hasRelatedWork W3170094116 @default.
- W4378465055 hasRelatedWork W3209574120 @default.
- W4378465055 hasRelatedWork W4205958290 @default.
- W4378465055 hasRelatedWork W4285260836 @default.
- W4378465055 hasRelatedWork W4286629047 @default.
- W4378465055 hasRelatedWork W4306321456 @default.
- W4378465055 hasRelatedWork W4306674287 @default.
- W4378465055 hasRelatedWork W4224009465 @default.
- W4378465055 isParatext "false" @default.
- W4378465055 isRetracted "false" @default.
- W4378465055 workType "article" @default.