Matches in SemOpenAlex for { <https://semopenalex.org/work/W2990963180> ?p ?o ?g. }
- W2990963180 abstract "Important information that relates to a specific topic in a document is often organized in tabular format to assist readers with information retrieval and comparison, which may be difficult to provide in natural language. However, tabular data in unstructured digital documents, e.g., Portable Document Format (PDF) and images, are difficult to parse into structured machine-readable format, due to complexity and diversity in their structure and style. To facilitate image-based table recognition with deep learning, we develop the largest publicly available table recognition dataset PubTabNet (https://github.com/ibm-aur-nlp/PubTabNet), containing 568k table images with corresponding structured HTML representation. PubTabNet is automatically generated by matching the XML and PDF representations of the scientific articles in PubMed Central Open Access Subset (PMCOA). We also propose a novel attention-based encoder-dual-decoder (EDD) architecture that converts images of tables into HTML code. The model has a structure decoder which reconstructs the table structure and helps the cell decoder to recognize cell content. In addition, we propose a new Tree-Edit-Distance-based Similarity (TEDS) metric for table recognition, which more appropriately captures multi-hop cell misalignment and OCR errors than the pre-established metric. The experiments demonstrate that the EDD model can accurately recognize complex tables solely relying on the image representation, outperforming the state-of-the-art by 9.7% absolute TEDS score." @default.
- W2990963180 created "2019-12-05" @default.
- W2990963180 creator A5007437126 @default.
- W2990963180 creator A5033797534 @default.
- W2990963180 creator A5077681143 @default.
- W2990963180 date "2019-11-24" @default.
- W2990963180 modified "2023-10-05" @default.
- W2990963180 title "Image-based table recognition: data, model, and evaluation" @default.
- W2990963180 cites W1514535095 @default.
- W2990963180 cites W1573796710 @default.
- W2990963180 cites W1647671624 @default.
- W2990963180 cites W1970549718 @default.
- W2990963180 cites W1990899722 @default.
- W2990963180 cites W2022351003 @default.
- W2990963180 cites W2046941907 @default.
- W2990963180 cites W2051265407 @default.
- W2990963180 cites W2098218583 @default.
- W2990963180 cites W2104875837 @default.
- W2990963180 cites W2111297753 @default.
- W2990963180 cites W2117462434 @default.
- W2990963180 cites W2128863362 @default.
- W2990963180 cites W2150673968 @default.
- W2990963180 cites W2166323498 @default.
- W2990963180 cites W2194775991 @default.
- W2990963180 cites W2407128951 @default.
- W2990963180 cites W2444353601 @default.
- W2990963180 cites W2613718673 @default.
- W2990963180 cites W2786162033 @default.
- W2990963180 cites W2786480153 @default.
- W2990963180 cites W2787523828 @default.
- W2990963180 cites W2795424778 @default.
- W2990963180 cites W2921906393 @default.
- W2990963180 cites W2948838566 @default.
- W2990963180 cites W2955530511 @default.
- W2990963180 cites W2963037989 @default.
- W2990963180 cites W2963150697 @default.
- W2990963180 cites W2963311793 @default.
- W2990963180 cites W2964121744 @default.
- W2990963180 cites W2971712385 @default.
- W2990963180 cites W2998913931 @default.
- W2990963180 cites W3003496674 @default.
- W2990963180 cites W3003514020 @default.
- W2990963180 cites W3003711898 @default.
- W2990963180 cites W3003931580 @default.
- W2990963180 cites W3004042913 @default.
- W2990963180 cites W3104358146 @default.
- W2990963180 doi "https://doi.org/10.48550/arxiv.1911.10683" @default.
- W2990963180 hasPublicationYear "2019" @default.
- W2990963180 type Work @default.
- W2990963180 sameAs 2990963180 @default.
- W2990963180 citedByCount "21" @default.
- W2990963180 countsByYear W29909631802020 @default.
- W2990963180 countsByYear W29909631802021 @default.
- W2990963180 countsByYear W29909631802022 @default.
- W2990963180 crossrefType "posted-content" @default.
- W2990963180 hasAuthorship W2990963180A5007437126 @default.
- W2990963180 hasAuthorship W2990963180A5033797534 @default.
- W2990963180 hasAuthorship W2990963180A5077681143 @default.
- W2990963180 hasBestOaLocation W29909631801 @default.
- W2990963180 hasConcept C124101348 @default.
- W2990963180 hasConcept C136764020 @default.
- W2990963180 hasConcept C153180895 @default.
- W2990963180 hasConcept C154945302 @default.
- W2990963180 hasConcept C17744445 @default.
- W2990963180 hasConcept C186644900 @default.
- W2990963180 hasConcept C199539241 @default.
- W2990963180 hasConcept C204321447 @default.
- W2990963180 hasConcept C23123220 @default.
- W2990963180 hasConcept C2776359362 @default.
- W2990963180 hasConcept C41008148 @default.
- W2990963180 hasConcept C45235069 @default.
- W2990963180 hasConcept C68476402 @default.
- W2990963180 hasConcept C68699486 @default.
- W2990963180 hasConcept C8797682 @default.
- W2990963180 hasConcept C94625758 @default.
- W2990963180 hasConceptScore W2990963180C124101348 @default.
- W2990963180 hasConceptScore W2990963180C136764020 @default.
- W2990963180 hasConceptScore W2990963180C153180895 @default.
- W2990963180 hasConceptScore W2990963180C154945302 @default.
- W2990963180 hasConceptScore W2990963180C17744445 @default.
- W2990963180 hasConceptScore W2990963180C186644900 @default.
- W2990963180 hasConceptScore W2990963180C199539241 @default.
- W2990963180 hasConceptScore W2990963180C204321447 @default.
- W2990963180 hasConceptScore W2990963180C23123220 @default.
- W2990963180 hasConceptScore W2990963180C2776359362 @default.
- W2990963180 hasConceptScore W2990963180C41008148 @default.
- W2990963180 hasConceptScore W2990963180C45235069 @default.
- W2990963180 hasConceptScore W2990963180C68476402 @default.
- W2990963180 hasConceptScore W2990963180C68699486 @default.
- W2990963180 hasConceptScore W2990963180C8797682 @default.
- W2990963180 hasConceptScore W2990963180C94625758 @default.
- W2990963180 hasLocation W29909631801 @default.
- W2990963180 hasOpenAccess W2990963180 @default.
- W2990963180 hasPrimaryLocation W29909631801 @default.
- W2990963180 hasRelatedWork W2083429127 @default.
- W2990963180 hasRelatedWork W2366867683 @default.
- W2990963180 hasRelatedWork W2392917763 @default.
- W2990963180 hasRelatedWork W2948670949 @default.
- W2990963180 hasRelatedWork W2952780262 @default.
- W2990963180 hasRelatedWork W2979495269 @default.