Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385221022> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4385221022 endingPage "296" @default.
- W4385221022 startingPage "296" @default.
- W4385221022 abstract "Address parsing is a crucial task in natural language processing, particularly for Chinese addresses. The complex structure and semantic features of Chinese addresses present challenges due to their inherent ambiguity. Additionally, different task scenarios require varying levels of granularity in address components, further complicating the parsing process. To address these challenges and adapt to low-resource environments, we propose CapICL, a novel Chinese address parsing model based on the In-Context Learning (ICL) framework. CapICL leverages a sequence generator, regular expression matching, BERT semantic similarity computation, and Generative Pre-trained Transformer (GPT) modeling to enhance parsing accuracy by incorporating contextual information. We construct the sequence generator using a small annotated dataset, capturing distribution patterns and boundary features of address types to model address structure and semantics, which mitigates interference from unnecessary variations. We introduce the REB–KNN algorithm, which selects similar samples for ICL-based parsing using regular expression matching and BERT semantic similarity computation. The selected samples, raw text, and explanatory text are combined to form prompts and inputted into the GPT model for prediction and address parsing. Experimental results demonstrate significant achievements of CapICL in low-resource environments, reducing dependency on annotated data and computational resources. Our model’s effectiveness, adaptability, and broad application potential are validated, showcasing its positive impact in natural language processing and geographical information systems." @default.
- W4385221022 created "2023-07-25" @default.
- W4385221022 creator A5053510836 @default.
- W4385221022 creator A5065190048 @default.
- W4385221022 creator A5069918577 @default.
- W4385221022 creator A5080374958 @default.
- W4385221022 date "2023-07-22" @default.
- W4385221022 modified "2023-09-27" @default.
- W4385221022 title "Enhancing Chinese Address Parsing in Low-Resource Scenarios through In-Context Learning" @default.
- W4385221022 cites W2790313525 @default.
- W4385221022 cites W2909828422 @default.
- W4385221022 cites W2963642108 @default.
- W4385221022 cites W2970476646 @default.
- W4385221022 cites W2970641574 @default.
- W4385221022 cites W2973619314 @default.
- W4385221022 cites W3024097351 @default.
- W4385221022 cites W3100806282 @default.
- W4385221022 cites W3114319529 @default.
- W4385221022 cites W3122241445 @default.
- W4385221022 cites W3156470785 @default.
- W4385221022 cites W3168656614 @default.
- W4385221022 cites W3172642864 @default.
- W4385221022 cites W3173777717 @default.
- W4385221022 cites W3175552668 @default.
- W4385221022 cites W3176023514 @default.
- W4385221022 cites W3185341429 @default.
- W4385221022 cites W4212903126 @default.
- W4385221022 cites W4221148939 @default.
- W4385221022 cites W4285089646 @default.
- W4385221022 cites W4306680578 @default.
- W4385221022 cites W4310154945 @default.
- W4385221022 cites W4327499192 @default.
- W4385221022 doi "https://doi.org/10.3390/ijgi12070296" @default.
- W4385221022 hasPublicationYear "2023" @default.
- W4385221022 type Work @default.
- W4385221022 citedByCount "0" @default.
- W4385221022 crossrefType "journal-article" @default.
- W4385221022 hasAuthorship W4385221022A5053510836 @default.
- W4385221022 hasAuthorship W4385221022A5065190048 @default.
- W4385221022 hasAuthorship W4385221022A5069918577 @default.
- W4385221022 hasAuthorship W4385221022A5080374958 @default.
- W4385221022 hasBestOaLocation W43852210221 @default.
- W4385221022 hasConcept C151730666 @default.
- W4385221022 hasConcept C154945302 @default.
- W4385221022 hasConcept C164883195 @default.
- W4385221022 hasConcept C186644900 @default.
- W4385221022 hasConcept C195324797 @default.
- W4385221022 hasConcept C204321447 @default.
- W4385221022 hasConcept C2779343474 @default.
- W4385221022 hasConcept C2779439875 @default.
- W4385221022 hasConcept C41008148 @default.
- W4385221022 hasConcept C86803240 @default.
- W4385221022 hasConceptScore W4385221022C151730666 @default.
- W4385221022 hasConceptScore W4385221022C154945302 @default.
- W4385221022 hasConceptScore W4385221022C164883195 @default.
- W4385221022 hasConceptScore W4385221022C186644900 @default.
- W4385221022 hasConceptScore W4385221022C195324797 @default.
- W4385221022 hasConceptScore W4385221022C204321447 @default.
- W4385221022 hasConceptScore W4385221022C2779343474 @default.
- W4385221022 hasConceptScore W4385221022C2779439875 @default.
- W4385221022 hasConceptScore W4385221022C41008148 @default.
- W4385221022 hasConceptScore W4385221022C86803240 @default.
- W4385221022 hasFunder F4320335777 @default.
- W4385221022 hasIssue "7" @default.
- W4385221022 hasLocation W43852210221 @default.
- W4385221022 hasLocation W43852210222 @default.
- W4385221022 hasOpenAccess W4385221022 @default.
- W4385221022 hasPrimaryLocation W43852210221 @default.
- W4385221022 hasRelatedWork W2020540721 @default.
- W4385221022 hasRelatedWork W2293457016 @default.
- W4385221022 hasRelatedWork W2502722637 @default.
- W4385221022 hasRelatedWork W2977842567 @default.
- W4385221022 hasRelatedWork W3153750606 @default.
- W4385221022 hasRelatedWork W3198474835 @default.
- W4385221022 hasRelatedWork W4226226396 @default.
- W4385221022 hasRelatedWork W4308854837 @default.
- W4385221022 hasRelatedWork W1872130062 @default.
- W4385221022 hasRelatedWork W2153799799 @default.
- W4385221022 hasVolume "12" @default.
- W4385221022 isParatext "false" @default.
- W4385221022 isRetracted "false" @default.
- W4385221022 workType "article" @default.