Optimized Table Tokenization for Table Structure Recognition

• URL: http://arxiv.org/abs/2305.03393v1
• Date: Fri, 5 May 2023 09:38:47 GMT
• Title: Optimized Table Tokenization for Table Structure Recognition
• Authors: Maksym Lysak, Ahmed Nassar, Nikolaos Livathinos, Christoph Auer, Peter Staar
• Abstract summary: transformer-based models have demonstrated that table-structure can be recognized with impressive accuracy using Image-to-Markup-Sequence approaches. Taking only the image of a table, such models predict a sequence of tokens which represent the structure of the table. We propose a new, optimised table-structure language (OTSL) with a minimized vocabulary and specific rules.
• Score: 2.9398911304923447
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Extracting tables from documents is a crucial task in any document conversion pipeline. Recently, transformer-based models have demonstrated that table-structure can be recognized with impressive accuracy using Image-to-Markup-Sequence (Im2Seq) approaches. Taking only the image of a table, such models predict a sequence of tokens (e.g. in HTML, LaTeX) which represent the structure of the table. Since the token representation of the table structure has a significant impact on the accuracy and run-time performance of any Im2Seq model, we investigate in this paper how table-structure representation can be optimised. We propose a new, optimised table-structure language (OTSL) with a minimized vocabulary and specific rules. The benefits of OTSL are that it reduces the number of tokens to 5 (HTML needs 28+) and shortens the sequence length to half of HTML on average. Consequently, model accuracy improves significantly, inference time is halved compared to HTML-based models, and the predicted table structures are always syntactically correct. This in turn eliminates most post-processing needs.

Related papers

• SPRINT: Script-agnostic Structure Recognition in Tables [20.394597266150534]
  Table Structure Recognition (TSR) is vital for various downstream tasks like information retrieval, table reconstruction, and document understanding. We propose TSR as a language-agnostic cell arrangement prediction and introduce SPRINT, Script-agnostic Structure Recognition in Tables. We experimentally evaluate our performance across benchmark TSR datasets including PubTabNet, FinTabNet, and PubTables-1M.
  arXiv  Detail & Related papers  (2025-03-15T00:43:53Z)
• UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognition [55.153629718464565]
  We introduce UniTabNet, a novel framework for table structure parsing based on the image-to-text model. UniTabNet employs a divide-and-conquer'' strategy, utilizing an image-to-text model to decouple table cells and integrating both physical and logical decoders to reconstruct the complete table structure.
  arXiv  Detail & Related papers  (2024-09-20T01:26:32Z)
• SEMv2: Table Separation Line Detection Based on Instance Segmentation [96.36188168694781]
  We propose an accurate table structure recognizer, termed SEMv2 (SEM: Split, Embed and Merge) We address the table separation line instance-level discrimination problem and introduce a table separation line detection strategy based on conditional convolution. To comprehensively evaluate the SEMv2, we also present a more challenging dataset for table structure recognition, dubbed iFLYTAB.
  arXiv  Detail & Related papers  (2023-03-08T05:15:01Z)
• ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples [15.212332890570869]
  We develop ReasTAP to show that high-level table reasoning skills can be injected into models during pre-training without a complex table-specific architecture design. ReasTAP achieves new state-of-the-art performance on all benchmarks and delivers a significant improvement on low-resource setting.
  arXiv  Detail & Related papers  (2022-10-22T07:04:02Z)
• Table Retrieval May Not Necessitate Table-specific Model Design [83.27735758203089]
  We focus on the task of table retrieval, and ask: "is table-specific model design necessary for table retrieval?" Based on an analysis on a table-based portion of the Natural Questions dataset (NQ-table), we find that structure plays a negligible role in more than 70% of the cases. We then experiment with three modules to explicitly encode table structures, namely auxiliary row/column embeddings, hard attention masks, and soft relation-based attention biases. None of these yielded significant improvements, suggesting that table-specific model design may not be necessary for table retrieval.
  arXiv  Detail & Related papers  (2022-05-19T20:35:23Z)
• TableFormer: Table Structure Understanding with Transformers [2.121963121603413]
  We present a new table-structure identification model. New object detection decoder for table-cells. Second, we replace the LSTM decoders with transformer based decoders.
  arXiv  Detail & Related papers  (2022-03-02T10:46:24Z)
• TableFormer: Robust Transformer Modeling for Table-Text Encoding [18.00127368618485]
  Existing models for table understanding require linearization of the table structure, where row or column order is encoded as an unwanted bias. In this work, we propose a robust and structurally aware table-text encoding architecture TableFormer.
  arXiv  Detail & Related papers  (2022-03-01T07:23:06Z)
• Multi-Type-TD-TSR -- Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition: from OCR to Structured Table Representations [63.98463053292982]
  The recognition of tables consists of two main tasks, namely table detection and table structure recognition. Recent work shows a clear trend towards deep learning approaches coupled with the use of transfer learning for the task of table structure recognition. We present a multistage pipeline named Multi-Type-TD-TSR, which offers an end-to-end solution for the problem of table recognition.
  arXiv  Detail & Related papers  (2021-05-23T21:17:18Z)
• A Graph Representation of Semi-structured Data for Web Question Answering [96.46484690047491]
  We propose a novel graph representation of Web tables and lists based on a systematic categorization of the components in semi-structured data as well as their relations. Our method improves F1 score by 3.90 points over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-10-14T04:01:54Z)
• Understanding tables with intermediate pre-training [11.96734018295146]
  We adapt TAPAS, a table-based BERT model, to recognize entailment. We evaluate table pruning techniques as a pre-processing step to drastically improve the training and prediction efficiency.
  arXiv  Detail & Related papers  (2020-10-01T17:43:27Z)
• GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing [117.98107557103877]
  We present GraPPa, an effective pre-training approach for table semantic parsing. We construct synthetic question-pairs over high-free tables via a synchronous context-free grammar. To maintain the model's ability to represent real-world data, we also include masked language modeling.
  arXiv  Detail & Related papers  (2020-09-29T08:17:58Z)
• Table Structure Extraction with Bi-directional Gated Recurrent Unit Networks [5.350788087718877]
  This paper proposes a robust deep learning based approach to extract rows and columns from a detected table in document images with a high precision. We have benchmarked our system on publicly available UNLV as well as ICDAR 2013 datasets on which it outperformed the state-of-the-art table structure extraction systems by a significant margin.
  arXiv  Detail & Related papers  (2020-01-08T13:17:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.