Sökning: id:"swepub:oai:DiVA.org:hh-52317" > Document-level Rela...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 03504naa a2200409 4500 | |
001 | oai:DiVA.org:hh-52317 | |
003 | SwePub | |
008 | 231222s2024 | |||||||||||000 ||eng| | |
024 | 7 | a https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-523172 URI |
024 | 7 | a https://doi.org/10.1016/j.neunet.2023.11.0622 DOI |
040 | a (SwePub)hh | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a ref2 swepub-contenttype |
072 | 7 | a art2 swepub-publicationtype |
100 | 1 | a Han, Ridongu Jilin University, Changchun, China4 aut |
245 | 1 0 | a Document-level Relation Extraction with Relation Correlations |
264 | 1 | a Oxford :b Elsevier,c 2024 |
338 | a print2 rdacarrier | |
500 | a Funding: This work is supported by the National Natural Science Foundation of China under grant No. 61872163 and 61806084, Jilin Province Key Scientific and Technological Research and Development Project under grant No. 20210201131GX, and Jilin Provincial Education Department Project under grant No. JJKH20190160KJ. | |
520 | a Document-level relation extraction faces two often overlooked challenges: long-tail problem and multi-label problem. Previous work focuses mainly on obtaining better contextual representations for entity pairs, hardly address the above challenges. In this paper, we analyze the co-occurrence correlation of relations, and introduce it into the document-level relation extraction task for the first time. We argue that the correlations can not only transfer knowledge between data-rich relations and data-scarce ones to assist in the training of long-tailed relations, but also reflect semantic distance guiding the classifier to identify semantically close relations for multi-label entity pairs. Specifically, we use relation embedding as a medium, and propose two co-occurrence prediction sub-tasks from both coarse- and fine-grained perspectives to capture relation correlations. Finally, the learned correlation-aware embeddings are used to guide the extraction of relational facts. Substantial experiments on two popular datasets (i.e., DocRED and DWIE) are conducted, and our method achieves superior results compared to baselines. Insightful analysis also demonstrates the potential of relation correlations to address the above challenges. The data and code are released at https://github.com/RidongHan/DocRE-Co-Occur. © 2023 Elsevier Ltd | |
650 | 7 | a NATURVETENSKAPx Data- och informationsvetenskapx Språkteknologi0 (SwePub)102082 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Computer and Information Sciencesx Language Technology0 (SwePub)102082 hsv//eng |
653 | a Co-occurrence | |
653 | a Document-level | |
653 | a Multi-task | |
653 | a Relation Correlations | |
653 | a Relation Extraction | |
700 | 1 | a Peng, Taou Jilin University, Changchun, China4 aut |
700 | 1 | a Wang, Benyouu The Chinese University of Hong Kong, Shenzhen, China4 aut |
700 | 1 | a Liu, Luu Jilin University, Changchun, China4 aut |
700 | 1 | a Tiwari, Prayag,d 1991-u Högskolan i Halmstad,Akademin för informationsteknologi4 aut0 (Swepub:hh)pratiw |
700 | 1 | a Wan, Xiangu The Chinese University of Hong Kong, Shenzhen, China4 aut |
710 | 2 | a Jilin University, Changchun, Chinab The Chinese University of Hong Kong, Shenzhen, China4 org |
773 | 0 | t Neural Networksd Oxford : Elsevierg 171, s. 14-24q 171<14-24x 0893-6080x 1879-2782 |
856 | 4 8 | u https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-52317 |
856 | 4 8 | u https://doi.org/10.1016/j.neunet.2023.11.062 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.