Sebastián Gallardo Díaz, Dorian Mazauric, Pierre Kornprobst
Simply transposing the print newspapers into digital media can not be satisfactory because they were not designed for small displays. One key feature lost is the notion of entry points that are essential for navigation. By focusing on headlines as entry points, we show how to produce alternative layouts for small displays that preserve entry points quality (readability and usability) while optimizing aesthetics and style. Our approach consists in a relayouting approach implemented via a genetic-inspired approach. We tested it on realistic newspaper pages. For the case discussed here, we obtained more than 2000 different layouts where the font was increased by a factor of two. We show that the quality of headlines is globally much better with the new layouts than with the original layout. Future work will tend to generalize this promising approach, accounting for the complexity of real newspapers, with user experience quality as the primary goal.
{"title":"From print to online newspapers on small displays: a layout generation approach aimed at preserving entry points","authors":"Sebastián Gallardo Díaz, Dorian Mazauric, Pierre Kornprobst","doi":"10.1145/3558100.3563847","DOIUrl":"https://doi.org/10.1145/3558100.3563847","url":null,"abstract":"Simply transposing the print newspapers into digital media can not be satisfactory because they were not designed for small displays. One key feature lost is the notion of entry points that are essential for navigation. By focusing on headlines as entry points, we show how to produce alternative layouts for small displays that preserve entry points quality (readability and usability) while optimizing aesthetics and style. Our approach consists in a relayouting approach implemented via a genetic-inspired approach. We tested it on realistic newspaper pages. For the case discussed here, we obtained more than 2000 different layouts where the font was increased by a factor of two. We show that the quality of headlines is globally much better with the new layouts than with the original layout. Future work will tend to generalize this promising approach, accounting for the complexity of real newspapers, with user experience quality as the primary goal.","PeriodicalId":146244,"journal":{"name":"Proceedings of the 22nd ACM Symposium on Document Engineering","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115659127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Erika Spiteri Bailey, Alexandra Bonnici, Stefania Cristina
In recent years, Page Object Detection (POD) has become a popular document understanding task, proving to be a non-trivial task given the potential complexity of documents. The rise of neural networks facilitated a more general learning approach to this task. However, in the literature, the different objects such as formulae, or figures among others, are generally considered individually. In this paper, we describe the joint localisation of six object classes relevant to scientific papers, namely isolated formulae, embedded formulae, figures, tables, variables and references. Through a qualitative analysis of these object classes, we note a hierarchy among the classes and propose a new localisation approach, using two, cascaded You Only Look Once (YOLO) networks. We also present a new data set consisting of labelled bounding boxes for all six object classes. This data set combines two commonly used data sets in the literature for formulae localisation, adding to the document images in these data sets the labels for figures, tables, variables and references. Using this data set, we achieve an average F1-score of 0.755 across all classes, which is comparable to the state-of-the-art for the object classes when considered individually for localisation.
近年来，页面对象检测(POD)已成为一种流行的文档理解任务，鉴于文档的潜在复杂性，它被证明是一项重要的任务。神经网络的兴起促进了一种更通用的学习方法来完成这项任务。然而，在文献中，不同的对象，如公式或数字等，通常是单独考虑的。在本文中，我们描述了与科学论文相关的六类对象的联合定位，即孤立公式、嵌入公式、图形、表格、变量和参考文献。通过对这些对象类的定性分析，我们注意到类之间的层次结构，并提出了一种新的定位方法，使用两个级联的You Only Look Once (YOLO)网络。我们还提出了一个由所有六个对象类的标记边界框组成的新数据集。该数据集结合了文献中常用的两个数据集进行公式定位，在这些数据集中的文档图像上添加了图形、表格、变量和参考文献的标签。使用这个数据集，我们在所有类中获得了0.755的平均f1分数，当单独考虑对象类进行本地化时，这与对象类的最新水平相当。
{"title":"A cascaded approach for page-object detection in scientific papers","authors":"Erika Spiteri Bailey, Alexandra Bonnici, Stefania Cristina","doi":"10.1145/3558100.3563851","DOIUrl":"https://doi.org/10.1145/3558100.3563851","url":null,"abstract":"In recent years, Page Object Detection (POD) has become a popular document understanding task, proving to be a non-trivial task given the potential complexity of documents. The rise of neural networks facilitated a more general learning approach to this task. However, in the literature, the different objects such as formulae, or figures among others, are generally considered individually. In this paper, we describe the joint localisation of six object classes relevant to scientific papers, namely isolated formulae, embedded formulae, figures, tables, variables and references. Through a qualitative analysis of these object classes, we note a hierarchy among the classes and propose a new localisation approach, using two, cascaded You Only Look Once (YOLO) networks. We also present a new data set consisting of labelled bounding boxes for all six object classes. This data set combines two commonly used data sets in the literature for formulae localisation, adding to the document images in these data sets the labels for figures, tables, variables and references. Using this data set, we achieve an average F1-score of 0.755 across all classes, which is comparable to the state-of-the-art for the object classes when considered individually for localisation.","PeriodicalId":146244,"journal":{"name":"Proceedings of the 22nd ACM Symposium on Document Engineering","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122391431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Research on writing tools stopped in the late 1980s when Microsoft Word had achieved monopoly status. However, the development of the Web and the advent of mobile devices are increasingly rendering static print-like documents obsolete. In this vision paper we reflect on the impact of this development on scholarly writing and publishing. Academic publications increasingly include dynamic elements, e.g., code, data plots, and other visualizations, which clearly requires other tools for document production than traditional word processors. When the printed page no longer is the desired final product, content and form can be addressed explicitly and separately, thus emphasizing the structure of texts rather than the structure of documents. The resulting challenges have not yet been fully addressed by document engineering.
{"title":"Academic writing and publishing beyond documents","authors":"C. Mahlow, M. Piotrowski","doi":"10.1145/3558100.3563840","DOIUrl":"https://doi.org/10.1145/3558100.3563840","url":null,"abstract":"Research on writing tools stopped in the late 1980s when Microsoft Word had achieved monopoly status. However, the development of the Web and the advent of mobile devices are increasingly rendering static print-like documents obsolete. In this vision paper we reflect on the impact of this development on scholarly writing and publishing. Academic publications increasingly include dynamic elements, e.g., code, data plots, and other visualizations, which clearly requires other tools for document production than traditional word processors. When the printed page no longer is the desired final product, content and form can be addressed explicitly and separately, thus emphasizing the structure of texts rather than the structure of documents. The resulting challenges have not yet been fully addressed by document engineering.","PeriodicalId":146244,"journal":{"name":"Proceedings of the 22nd ACM Symposium on Document Engineering","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117283329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. Lins, R. Bernardino, Ricardo da Silva Barboza, S. Simske
Today, over eighty percent of the world's population owns a smart-phone with an in-built camera, and they are very often used to photograph documents. Document binarization is a key process in many document processing platforms. This competition on binarizing photographed documents assessed the quality, time, space, and performance of five new algorithms and sixty-four "classical" and alternative algorithms. The evaluation dataset is composed of offset, laser, and deskjet printed documents, photographed using six widely-used mobile devices with the strobe flash on and off, under two different angles and places of capture.
{"title":"Binarization of photographed documents image quality, processing time and size assessment","authors":"R. Lins, R. Bernardino, Ricardo da Silva Barboza, S. Simske","doi":"10.1145/3558100.3564159","DOIUrl":"https://doi.org/10.1145/3558100.3564159","url":null,"abstract":"Today, over eighty percent of the world's population owns a smart-phone with an in-built camera, and they are very often used to photograph documents. Document binarization is a key process in many document processing platforms. This competition on binarizing photographed documents assessed the quality, time, space, and performance of five new algorithms and sixty-four \"classical\" and alternative algorithms. The evaluation dataset is composed of offset, laser, and deskjet printed documents, photographed using six widely-used mobile devices with the strobe flash on and off, under two different angles and places of capture.","PeriodicalId":146244,"journal":{"name":"Proceedings of the 22nd ACM Symposium on Document Engineering","volume":"767 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116137288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Luis Ángel Redondo-Gutierrez, Francisco Jáñez-Martino, Eduardo FIDALGO, Enrique Alegre, V. González-Castro, R. Alaíz-Rodríguez
Spam has become an effective way for cybercriminals to spread malware. Although cybersecurity agencies and companies develop products and organise courses for people to detect malicious spam email patterns, spam attacks are not totally avoided yet. In this work, we present and make publicly available "Spam Email Malware Detection - 600" (SEMD-600), a new dataset, based on Bruce Guenter's, for malware detection in spam using only the text of the email. We also introduce a pipeline for malware detection based on traditional Natural Language Processing (NLP) techniques. Using SEMD-600, we compare the text representation techniques Bag of Words and Term Frequency-Inverse Document Frequency (TF-IDF), in combination with three different supervised classifiers: Support Vector Machine, Naive Bayes and Logistic Regression, to detect malware in plain text documents. We found that combining TF-IDF with Logistic Regression achieved the best performance, with a macro F1 score of 0.763.
{"title":"Detecting malware using text documents extracted from spam email through machine learning","authors":"Luis Ángel Redondo-Gutierrez, Francisco Jáñez-Martino, Eduardo FIDALGO, Enrique Alegre, V. González-Castro, R. Alaíz-Rodríguez","doi":"10.1145/3558100.3563854","DOIUrl":"https://doi.org/10.1145/3558100.3563854","url":null,"abstract":"Spam has become an effective way for cybercriminals to spread malware. Although cybersecurity agencies and companies develop products and organise courses for people to detect malicious spam email patterns, spam attacks are not totally avoided yet. In this work, we present and make publicly available \"Spam Email Malware Detection - 600\" (SEMD-600), a new dataset, based on Bruce Guenter's, for malware detection in spam using only the text of the email. We also introduce a pipeline for malware detection based on traditional Natural Language Processing (NLP) techniques. Using SEMD-600, we compare the text representation techniques Bag of Words and Term Frequency-Inverse Document Frequency (TF-IDF), in combination with three different supervised classifiers: Support Vector Machine, Naive Bayes and Logistic Regression, to detect malware in plain text documents. We found that combining TF-IDF with Logistic Regression achieved the best performance, with a macro F1 score of 0.763.","PeriodicalId":146244,"journal":{"name":"Proceedings of the 22nd ACM Symposium on Document Engineering","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124827044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The portable document format (PDF) is both versatile and complex, with a specification exceeding well over a thousand pages. For independent developers writing software that reads, displays, or transforms PDFs, it is difficult to comprehensively account for all of the potential variations that might exist in the wild. Compounding this problem are the usage agreements that often accompany purchased and proprietary PDFs, preventing end users from uploading a troublesome document as part of a bug report and limiting the set of test cases that can be made public for open source development. In this paper, pdf-mangler is presented as a solution to this problem. The goal of pdf-mangler is to remove information in the form of text, images, and vector graphics while retaining as much of the document structure and general visual appearance as possible. The intention is for pdf-mangler to be deployed as part of an automated bug reporting tool for PDF software.
{"title":"Anonymizing and obfuscating PDF content while preserving document structure","authors":"Charlotte Curtis","doi":"10.1145/3558100.3563849","DOIUrl":"https://doi.org/10.1145/3558100.3563849","url":null,"abstract":"The portable document format (PDF) is both versatile and complex, with a specification exceeding well over a thousand pages. For independent developers writing software that reads, displays, or transforms PDFs, it is difficult to comprehensively account for all of the potential variations that might exist in the wild. Compounding this problem are the usage agreements that often accompany purchased and proprietary PDFs, preventing end users from uploading a troublesome document as part of a bug report and limiting the set of test cases that can be made public for open source development. In this paper, pdf-mangler is presented as a solution to this problem. The goal of pdf-mangler is to remove information in the form of text, images, and vector graphics while retaining as much of the document structure and general visual appearance as possible. The intention is for pdf-mangler to be deployed as part of an automated bug reporting tool for PDF software.","PeriodicalId":146244,"journal":{"name":"Proceedings of the 22nd ACM Symposium on Document Engineering","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130184409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Melsbach, Sven Stahlmann, Stefan Hirschmeier, D. Schoder
Multi-label document classification is the task of assigning one or more labels to a document, and has become a common task in various businesses. Typically, current state-of-the-art models based on pretrained language models tackle this task without taking the textual information of label names into account, therefore omitting possibly valuable information. We present an approach that leverages this information stored in label names by reformulating the problem of multi label classification into a document similarity problem. To achieve this, we use a triplet transformer network that learns to embed labels and documents into a joint vector space. Our approach is fast at inference, classifying documents by determining the closest and therefore most similar labels. We evaluate our approach on a challenging real-world dataset of a German radio-broadcaster and find that our model provides competitive results compared to other established approaches.
{"title":"Triplet transformer network for multi-label document classification","authors":"J. Melsbach, Sven Stahlmann, Stefan Hirschmeier, D. Schoder","doi":"10.1145/3558100.3563843","DOIUrl":"https://doi.org/10.1145/3558100.3563843","url":null,"abstract":"Multi-label document classification is the task of assigning one or more labels to a document, and has become a common task in various businesses. Typically, current state-of-the-art models based on pretrained language models tackle this task without taking the textual information of label names into account, therefore omitting possibly valuable information. We present an approach that leverages this information stored in label names by reformulating the problem of multi label classification into a document similarity problem. To achieve this, we use a triplet transformer network that learns to embed labels and documents into a joint vector space. Our approach is fast at inference, classifying documents by determining the closest and therefore most similar labels. We evaluate our approach on a challenging real-world dataset of a German radio-broadcaster and find that our model provides competitive results compared to other established approaches.","PeriodicalId":146244,"journal":{"name":"Proceedings of the 22nd ACM Symposium on Document Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126248655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the midst of digital transformation, automatically understanding the structure and composition of scanned documents is important in order to allow correct indexing, archiving, and processing. In many organizations, different types of documents are usually scanned together in folders, so it is essential to automate the task of segmenting the folders into documents which then proceed to further analysis tailored to specific document types. This task is known as Page Stream Segmentation (PSS). In this paper, we propose a deep learning solution to solve the task of determining whether or not a page is a breaking-point given a sequence of scanned pages (a folder) as input. We also provide a dataset called TABME (TAB this folder of docuMEnts) generated specifically for this task. Our proposed architecture combines LayoutLM and ResNet to exploit both textual and visual features of the document pages and achieves an F1 score of 0.953. The dataset and code used to run the experiments in this paper are available at the following web link: https://github.com/aldolipani/TABME.
在数字化转换过程中，为了实现正确的索引、归档和处理，自动理解扫描文档的结构和组成非常重要。在许多组织中，不同类型的文档通常在文件夹中一起扫描，因此自动化将文件夹分割成文档的任务非常重要，然后根据特定的文档类型进行进一步分析。这个任务被称为页面流分割(PSS)。在本文中，我们提出了一个深度学习解决方案来解决给定扫描页面序列(文件夹)作为输入来确定页面是否为断点的任务。我们还提供了一个专门为此任务生成的名为TABME (TAB this folder of docuMEnts)的数据集。我们提出的架构结合了LayoutLM和ResNet来利用文档页面的文本和视觉特征，并获得了0.953的F1分数。用于运行本文中实验的数据集和代码可在以下web链接中获得:https://github.com/aldolipani/TABME。
{"title":"Tab this folder of documents: page stream segmentation of business documents","authors":"Thisanaporn Mungmeeprued, Yuxin Ma, Nisarg Mehta, Aldo Lipani","doi":"10.1145/3558100.3563852","DOIUrl":"https://doi.org/10.1145/3558100.3563852","url":null,"abstract":"In the midst of digital transformation, automatically understanding the structure and composition of scanned documents is important in order to allow correct indexing, archiving, and processing. In many organizations, different types of documents are usually scanned together in folders, so it is essential to automate the task of segmenting the folders into documents which then proceed to further analysis tailored to specific document types. This task is known as Page Stream Segmentation (PSS). In this paper, we propose a deep learning solution to solve the task of determining whether or not a page is a breaking-point given a sequence of scanned pages (a folder) as input. We also provide a dataset called TABME (TAB this folder of docuMEnts) generated specifically for this task. Our proposed architecture combines LayoutLM and ResNet to exploit both textual and visual features of the document pages and achieves an F1 score of 0.953. The dataset and code used to run the experiments in this paper are available at the following web link: https://github.com/aldolipani/TABME.","PeriodicalId":146244,"journal":{"name":"Proceedings of the 22nd ACM Symposium on Document Engineering","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116950370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Text recognition tasks are commonly solved by using a deep learning pipeline called CRNN. The classical CRNN is a sequence of a convolutional network, followed by a bidirectional LSTM and a CTC layer. In this paper, we perform an extensive analysis of the components of a CRNN to find what is crucial to the entire pipeline and what characteristics can be exchanged for a more effective choice. Given the results of our experiments, we propose two different architectures for the task of text recognition. The first model, CNN + CTC, is a combination of a convolutional model followed by a CTC layer. The second model, CNN + Tr + CTC, adds an encoder-only Transformers between the convolutional network and the CTC layer. To the best of our knowledge, this is the first time that a Transformers have been successfully trained using just CTC loss. To assess the capabilities of our proposed architectures, we train and evaluate them on the SROIE 2019 data set. Our CNN + CTC achieves an F1 score of 89.66% possessing only 4.7 million parameters. CNN + Tr + CTC attained an F1 score of 93.76% with 11 million parameters, which is almost 97% of the performance achieved by the TrOCR using 334 million parameters and more than 600 million synthetic images for pretraining.
{"title":"Optical character recognition with transformers and CTC","authors":"Israel Campiotti, R. Lotufo","doi":"10.1145/3558100.3563845","DOIUrl":"https://doi.org/10.1145/3558100.3563845","url":null,"abstract":"Text recognition tasks are commonly solved by using a deep learning pipeline called CRNN. The classical CRNN is a sequence of a convolutional network, followed by a bidirectional LSTM and a CTC layer. In this paper, we perform an extensive analysis of the components of a CRNN to find what is crucial to the entire pipeline and what characteristics can be exchanged for a more effective choice. Given the results of our experiments, we propose two different architectures for the task of text recognition. The first model, CNN + CTC, is a combination of a convolutional model followed by a CTC layer. The second model, CNN + Tr + CTC, adds an encoder-only Transformers between the convolutional network and the CTC layer. To the best of our knowledge, this is the first time that a Transformers have been successfully trained using just CTC loss. To assess the capabilities of our proposed architectures, we train and evaluate them on the SROIE 2019 data set. Our CNN + CTC achieves an F1 score of 89.66% possessing only 4.7 million parameters. CNN + Tr + CTC attained an F1 score of 93.76% with 11 million parameters, which is almost 97% of the performance achieved by the TrOCR using 334 million parameters and more than 600 million synthetic images for pretraining.","PeriodicalId":146244,"journal":{"name":"Proceedings of the 22nd ACM Symposium on Document Engineering","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127538270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Danrun Cao, Oussama Ahmia, Nicolas Béchet, P. Marteau
We present a processing pipeline for Chinese public procurement document harvesting, with the aim of producing strategic data with greater added value. It consists of three micro-modules: data collection, information extraction, database indexing. The information extraction part is implemented through a hybrid system which combines rule-based and machine learning approaches. Rule-based method is used for extracting information with presenting recurring morphological features, such as dates, amounts and contract awardee information. Machine learning method is used for trade detection in the title of procurement documents.
{"title":"Chinese public procurement document harvesting pipeline","authors":"Danrun Cao, Oussama Ahmia, Nicolas Béchet, P. Marteau","doi":"10.1145/3558100.3563848","DOIUrl":"https://doi.org/10.1145/3558100.3563848","url":null,"abstract":"We present a processing pipeline for Chinese public procurement document harvesting, with the aim of producing strategic data with greater added value. It consists of three micro-modules: data collection, information extraction, database indexing. The information extraction part is implemented through a hybrid system which combines rule-based and machine learning approaches. Rule-based method is used for extracting information with presenting recurring morphological features, such as dates, amounts and contract awardee information. Machine learning method is used for trade detection in the title of procurement documents.","PeriodicalId":146244,"journal":{"name":"Proceedings of the 22nd ACM Symposium on Document Engineering","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125112305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：