Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289533913> ?p ?o ?g. }
- W4289533913 abstract "Entity resolution is a widely studied problem with several proposals to match records across relations. Matching textual content is a widespread task in many applications, such as question answering and search. While recent methods achieve promising results for these two tasks, there is no clear solution for the more general problem of matching textual content and structured data. We introduce a framework that supports this new task in an unsupervised setting for any pair of corpora, being relational tables or text documents. Our method builds a fine-grained graph over the content of the corpora and derives word embeddings to represent the objects to match in a low dimensional space. The learned representation enables effective and efficient matching at different granularity, from relational tuples to text sentences and paragraphs. Our flexible framework can exploit pre-trained resources, but, differently from other solutions, it does not depends on their existence and achieves better quality performance in matching content when the vocab-ulary is domain specific. We also introduce optimizations in the graph creation process with an “expand and compress” approach that first identifies new valid relationships across elements, to improve matching, and then prunes nodes and edges, to reduce the graph size. Experiments on real use cases and public datasets show that our framework produces embeddings that outperform word embeddings and fine-tuned language models both in results' quality and in execution times." @default.
- W4289533913 created "2022-08-03" @default.
- W4289533913 creator A5011336242 @default.
- W4289533913 creator A5046145551 @default.
- W4289533913 creator A5068386835 @default.
- W4289533913 date "2022-05-01" @default.
- W4289533913 modified "2023-09-27" @default.
- W4289533913 title "Unsupervised Matching of Data and Text" @default.
- W4289533913 cites W1527463082 @default.
- W4289533913 cites W2029097226 @default.
- W4289533913 cites W2048092465 @default.
- W4289533913 cites W2048596679 @default.
- W4289533913 cites W2065398649 @default.
- W4289533913 cites W2111708605 @default.
- W4289533913 cites W2146008005 @default.
- W4289533913 cites W2146458746 @default.
- W4289533913 cites W2153225416 @default.
- W4289533913 cites W2250539671 @default.
- W4289533913 cites W2462891382 @default.
- W4289533913 cites W2561529111 @default.
- W4289533913 cites W2612872092 @default.
- W4289533913 cites W2798649495 @default.
- W4289533913 cites W2913318911 @default.
- W4289533913 cites W2923400109 @default.
- W4289533913 cites W2924309908 @default.
- W4289533913 cites W2951479072 @default.
- W4289533913 cites W2962756421 @default.
- W4289533913 cites W2963316155 @default.
- W4289533913 cites W2963323070 @default.
- W4289533913 cites W2963855739 @default.
- W4289533913 cites W2966720878 @default.
- W4289533913 cites W2970641574 @default.
- W4289533913 cites W3011807731 @default.
- W4289533913 cites W3034195663 @default.
- W4289533913 cites W3035140194 @default.
- W4289533913 cites W3035231859 @default.
- W4289533913 cites W3084740534 @default.
- W4289533913 cites W3093679380 @default.
- W4289533913 cites W3098620803 @default.
- W4289533913 cites W3103177583 @default.
- W4289533913 cites W3103250330 @default.
- W4289533913 cites W3104097132 @default.
- W4289533913 cites W3105625590 @default.
- W4289533913 doi "https://doi.org/10.1109/icde53745.2022.00084" @default.
- W4289533913 hasPublicationYear "2022" @default.
- W4289533913 type Work @default.
- W4289533913 citedByCount "2" @default.
- W4289533913 countsByYear W42895339132022 @default.
- W4289533913 crossrefType "proceedings-article" @default.
- W4289533913 hasAuthorship W4289533913A5011336242 @default.
- W4289533913 hasAuthorship W4289533913A5046145551 @default.
- W4289533913 hasAuthorship W4289533913A5068386835 @default.
- W4289533913 hasBestOaLocation W42895339132 @default.
- W4289533913 hasConcept C105795698 @default.
- W4289533913 hasConcept C111919701 @default.
- W4289533913 hasConcept C118615104 @default.
- W4289533913 hasConcept C118930307 @default.
- W4289533913 hasConcept C132525143 @default.
- W4289533913 hasConcept C138885662 @default.
- W4289533913 hasConcept C154945302 @default.
- W4289533913 hasConcept C162324750 @default.
- W4289533913 hasConcept C165064840 @default.
- W4289533913 hasConcept C165696696 @default.
- W4289533913 hasConcept C177774035 @default.
- W4289533913 hasConcept C187736073 @default.
- W4289533913 hasConcept C204321447 @default.
- W4289533913 hasConcept C23123220 @default.
- W4289533913 hasConcept C2780451532 @default.
- W4289533913 hasConcept C33923547 @default.
- W4289533913 hasConcept C38652104 @default.
- W4289533913 hasConcept C41008148 @default.
- W4289533913 hasConcept C41895202 @default.
- W4289533913 hasConcept C80444323 @default.
- W4289533913 hasConcept C90805587 @default.
- W4289533913 hasConceptScore W4289533913C105795698 @default.
- W4289533913 hasConceptScore W4289533913C111919701 @default.
- W4289533913 hasConceptScore W4289533913C118615104 @default.
- W4289533913 hasConceptScore W4289533913C118930307 @default.
- W4289533913 hasConceptScore W4289533913C132525143 @default.
- W4289533913 hasConceptScore W4289533913C138885662 @default.
- W4289533913 hasConceptScore W4289533913C154945302 @default.
- W4289533913 hasConceptScore W4289533913C162324750 @default.
- W4289533913 hasConceptScore W4289533913C165064840 @default.
- W4289533913 hasConceptScore W4289533913C165696696 @default.
- W4289533913 hasConceptScore W4289533913C177774035 @default.
- W4289533913 hasConceptScore W4289533913C187736073 @default.
- W4289533913 hasConceptScore W4289533913C204321447 @default.
- W4289533913 hasConceptScore W4289533913C23123220 @default.
- W4289533913 hasConceptScore W4289533913C2780451532 @default.
- W4289533913 hasConceptScore W4289533913C33923547 @default.
- W4289533913 hasConceptScore W4289533913C38652104 @default.
- W4289533913 hasConceptScore W4289533913C41008148 @default.
- W4289533913 hasConceptScore W4289533913C41895202 @default.
- W4289533913 hasConceptScore W4289533913C80444323 @default.
- W4289533913 hasConceptScore W4289533913C90805587 @default.
- W4289533913 hasLocation W42895339131 @default.
- W4289533913 hasLocation W42895339132 @default.
- W4289533913 hasOpenAccess W4289533913 @default.
- W4289533913 hasPrimaryLocation W42895339131 @default.
- W4289533913 hasRelatedWork W1483367581 @default.