Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385890348> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4385890348 abstract "Recent supervised models for event coding vastly outperform pattern-matching methods. However, their reliance solely on new annotations disregards the vast knowledge within expert databases, hindering their applicability to fine-grained classification. To address these limitations, we explore zero-shot approaches for political event ontology relation classification, by leveraging knowledge from established annotation codebooks. Our study encompasses both ChatGPT and a novel natural language inference (NLI) based approach named ZSP. ZSP adopts a tree-query framework that deconstructs the task into context, modality, and class disambiguation levels. This framework improves interpretability, efficiency, and adaptability to schema changes. By conducting extensive experiments on our newly curated datasets, we pinpoint the instability issues within ChatGPT and highlight the superior performance of ZSP. ZSP achieves an impressive 40% improvement in F1 score for fine-grained Rootcode classification. ZSP demonstrates competitive performance compared to supervised BERT models, positioning it as a valuable tool for event record validation and ontology development. Our work underscores the potential of leveraging transfer learning and existing expertise to enhance the efficiency and scalability of research in the field." @default.
- W4385890348 created "2023-08-17" @default.
- W4385890348 creator A5005002693 @default.
- W4385890348 creator A5011175397 @default.
- W4385890348 creator A5054154936 @default.
- W4385890348 creator A5057729042 @default.
- W4385890348 creator A5069844991 @default.
- W4385890348 creator A5074473139 @default.
- W4385890348 date "2023-08-15" @default.
- W4385890348 modified "2023-09-27" @default.
- W4385890348 title "Synthesizing Political Zero-Shot Relation Classification via Codebook Knowledge, NLI, and ChatGPT" @default.
- W4385890348 doi "https://doi.org/10.48550/arxiv.2308.07876" @default.
- W4385890348 hasPublicationYear "2023" @default.
- W4385890348 type Work @default.
- W4385890348 citedByCount "0" @default.
- W4385890348 crossrefType "posted-content" @default.
- W4385890348 hasAuthorship W4385890348A5005002693 @default.
- W4385890348 hasAuthorship W4385890348A5011175397 @default.
- W4385890348 hasAuthorship W4385890348A5054154936 @default.
- W4385890348 hasAuthorship W4385890348A5057729042 @default.
- W4385890348 hasAuthorship W4385890348A5069844991 @default.
- W4385890348 hasAuthorship W4385890348A5074473139 @default.
- W4385890348 hasBestOaLocation W43858903481 @default.
- W4385890348 hasConcept C119857082 @default.
- W4385890348 hasConcept C154945302 @default.
- W4385890348 hasConcept C177606310 @default.
- W4385890348 hasConcept C18903297 @default.
- W4385890348 hasConcept C204321447 @default.
- W4385890348 hasConcept C2776214188 @default.
- W4385890348 hasConcept C2781067378 @default.
- W4385890348 hasConcept C41008148 @default.
- W4385890348 hasConcept C48044578 @default.
- W4385890348 hasConcept C52146309 @default.
- W4385890348 hasConcept C77088390 @default.
- W4385890348 hasConcept C86803240 @default.
- W4385890348 hasConceptScore W4385890348C119857082 @default.
- W4385890348 hasConceptScore W4385890348C154945302 @default.
- W4385890348 hasConceptScore W4385890348C177606310 @default.
- W4385890348 hasConceptScore W4385890348C18903297 @default.
- W4385890348 hasConceptScore W4385890348C204321447 @default.
- W4385890348 hasConceptScore W4385890348C2776214188 @default.
- W4385890348 hasConceptScore W4385890348C2781067378 @default.
- W4385890348 hasConceptScore W4385890348C41008148 @default.
- W4385890348 hasConceptScore W4385890348C48044578 @default.
- W4385890348 hasConceptScore W4385890348C52146309 @default.
- W4385890348 hasConceptScore W4385890348C77088390 @default.
- W4385890348 hasConceptScore W4385890348C86803240 @default.
- W4385890348 hasLocation W43858903481 @default.
- W4385890348 hasOpenAccess W4385890348 @default.
- W4385890348 hasPrimaryLocation W43858903481 @default.
- W4385890348 hasRelatedWork W2016108640 @default.
- W4385890348 hasRelatedWork W3006943036 @default.
- W4385890348 hasRelatedWork W4200511449 @default.
- W4385890348 hasRelatedWork W4206534706 @default.
- W4385890348 hasRelatedWork W4229079080 @default.
- W4385890348 hasRelatedWork W4299487748 @default.
- W4385890348 hasRelatedWork W4310868770 @default.
- W4385890348 hasRelatedWork W4385957992 @default.
- W4385890348 hasRelatedWork W4385965371 @default.
- W4385890348 hasRelatedWork W4386025632 @default.
- W4385890348 isParatext "false" @default.
- W4385890348 isRetracted "false" @default.
- W4385890348 workType "article" @default.