arXiv (Cornell University) · 2019 · 37 citations · 31 references
ComputingBiomedical InformaticsComputer ScienceInformation RetrievalMachine LearningNatural Language ProcessingDeep LearningDocument Image AnalysisDocument RepresentationInformation ExtractionPattern RecognitionRepresentation LearningDual-encoder ModelsHtml ParsingImage RepresentationInformation Retrieval EvaluationTable ExtractionTable Information ExtractionTable RecognitionTable Structure Recognition
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.
31
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Kaiming He, Georgia Gkioxari, Piotr Dollár et al. · 2017 · 28.8K citations
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He, Ross Girshick et al. · arXiv (Cornell University) · 2015 · 18.2K citations · Full text
Binary codes capable of correcting deletions, insertions and reversals
V.I. Levenshtein · Soviet physics. Doklady · 1965 · 10.4K citations
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Kelvin Xu, Jimmy Ba, Ryan Kiros et al. · arXiv (Cornell University) · 2015 · 7.5K citations · Full text