Proceedings of the 21st ACM Symposium on Document Engineering最新文献

Session details: Systems for visual document analysis 会议细节:可视化文档分析系统

Proceedings of the 21st ACM Symposium on Document Engineering Pub Date : 2021-08-16 DOI: 10.1145/3482786

Tamir Hassan

引用次数: 0

Document engineering issues in malware analysis 恶意软件分析中的文档工程问题

Proceedings of the 21st ACM Symposium on Document Engineering Pub Date : 2021-08-16 DOI: 10.1145/3469096.3470950

Charles K. Nicholas, R. J. Joyce, S. Simske

引用次数: 0

Recognizing creative visual design: multiscale design characteristics in free-form web curation documents 识别创意视觉设计:自由形式网页策划文档中的多尺度设计特征

Proceedings of the 21st ACM Symposium on Document Engineering Pub Date : 2021-08-16 DOI: 10.1145/3469096.3469869

Ajit Jain, A. Kerne, Nic Lupfer, Gabriel Britain, Aaron Perrine, Y. Choe, J. Keyser, Ruihong Huang

{"title":"Recognizing creative visual design: multiscale design characteristics in free-form web curation documents","authors":"Ajit Jain, A. Kerne, Nic Lupfer, Gabriel Britain, Aaron Perrine, Y. Choe, J. Keyser, Ruihong Huang","doi":"10.1145/3469096.3469869","DOIUrl":"https://doi.org/10.1145/3469096.3469869","url":null,"abstract":"Multiscale design is the widely practiced use of space and scale to visually explore and articulate relationships. Free-form web curation (FFWC) is an approach to supporting multiscale design, involving creative strategies of collecting content, assembling it to juxtapose and organize, sketching, writing, shifting perspective to navigate, and exhibiting to share and collaborate. Our long term goal is to support design students with automatic, on demand feedback. We introduce a spatial clustering technique for recognizing multiscale design characteristics---scales and clusters---in FFWC documents. We perform quantitative evaluation to establish baseline performance. We contribute to human-centered AI by advancing fundamental human aspirations, through automatic recognizers of creative design, e.g., for representing and communicating abstract ideas. We develop implications, (1) for supporting people using content recognition in creative contexts, such as design education; (2) for overcoming design fixation with human-centered AI; and (3) for recognizing multiscale design characteristics.","PeriodicalId":423462,"journal":{"name":"Proceedings of the 21st ACM Symposium on Document Engineering","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132023464","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}

引用次数: 3

Session details: Security and sensitive documents 会话详细信息:安全和敏感文档

Proceedings of the 21st ACM Symposium on Document Engineering Pub Date : 2021-08-16 DOI: 10.1145/3482784

Charles K. Nicholas

引用次数: 0

Efficient clustering of short text streams using online-offline clustering 使用在线-离线聚类的短文本流的高效聚类

Proceedings of the 21st ACM Symposium on Document Engineering Pub Date : 2021-08-16 DOI: 10.1145/3469096.3469866

Md. Rashadul Hasan Rakib, N. Zeh, E. Milios

{"title":"Efficient clustering of short text streams using online-offline clustering","authors":"Md. Rashadul Hasan Rakib, N. Zeh, E. Milios","doi":"10.1145/3469096.3469866","DOIUrl":"https://doi.org/10.1145/3469096.3469866","url":null,"abstract":"Short text stream clustering is an important but challenging task since massive amount of text is generated from different sources such as micro-blogging, question-answering, and social news aggregation websites. The two major challenges of clustering such massive amount of text is to cluster them within a reasonable amount of time and to achieve better clustering result. To overcome these two challenges, we propose an efficient short text stream clustering algorithm (called EStream) consisting of two modules: online and offline. The online module of EStream algorithm assigns a text to a cluster one by one as it arrives. To assign a text to a cluster it computes similarity between a text and a selected number of clusters instead of all clusters and thus significantly reduces the running time of the clustering of short text streams. EStream assigns a text to a cluster (new or existing) using the dynamically computed similarity thresholds. Thus EStream efficiently deals with the concept drift problem. The offline module of EStream algorithm enhances the distributions of texts in the clusters obtained by the online module so that the upcoming short texts can be assigned to the appropriate clusters. Experimental results demonstrate that EStream outperforms the state-of-the-art short text stream clustering methods (in terms of clustering result) by a statistically significant margin on several short text datasets. Moreover, the running time of EStream is several orders of magnitude faster than that of the state-of-the-art methods.","PeriodicalId":423462,"journal":{"name":"Proceedings of the 21st ACM Symposium on Document Engineering","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122071169","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}

引用次数: 4

Text line extraction using deep learning and minimal sub seams 文本线提取使用深度学习和最小子接缝

Proceedings of the 21st ACM Symposium on Document Engineering Pub Date : 2021-08-16 DOI: 10.1145/3469096.3474941

Adi Azran, A. Schclar, Raid Saabni

{"title":"Text line extraction using deep learning and minimal sub seams","authors":"Adi Azran, A. Schclar, Raid Saabni","doi":"10.1145/3469096.3474941","DOIUrl":"https://doi.org/10.1145/3469096.3474941","url":null,"abstract":"Accurate text line extraction is a vital prerequisite for efficient and successful text recognition systems ranging from keywords/phrases searching to complete conversion to text. In many cases, the proposed algorithms target binary pre-processed versions of the image, which may cause insufficient results due to poor quality document images. Recently, more papers present solutions that work directly on gray-level images [1,2,7,12,15]. In this paper, we present a novel robust, and efficient algorithm to extract text-lines directly from gray-level document images. The proposed approach uses a combination of two variants of Convolutional Neural Network (CNNs), followed by minimal energy seam extraction. The first ConvNet is a modified version of the autoencoder used for biomedical image segmentation [8]. The second is a deep convolutional Neural Network, working on overlapping vertical slices of the original image. The two variants are combined to one neural net after re-attaching the resulting slices of the second net. The merged results of the two nets are used as a preprocessed image to obtain an energy map for a second phase. In the second step, we use the algorithm presented in [2], to track minimal energy sub-seams accumulated to perform a full local minimal/maximal separating and medial seam defining the text baselines and the text line regions. We have tested our approach on multi-lingual various datasets written at a range of image quality based on the ICDAR datasets.","PeriodicalId":423462,"journal":{"name":"Proceedings of the 21st ACM Symposium on Document Engineering","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128738189","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}

引用次数: 1

MTLV MTLV

Proceedings of the 21st ACM Symposium on Document Engineering Pub Date : 2021-08-16 DOI: 10.1145/3469096.3474926

Fatemeh Rahimi, Evangelos E. Milios, S. Matwin

{"title":"MTLV","authors":"Fatemeh Rahimi, Evangelos E. Milios, S. Matwin","doi":"10.1145/3469096.3474926","DOIUrl":"https://doi.org/10.1145/3469096.3474926","url":null,"abstract":"Multi-Task Learning (MTL) for text classification takes advantage of the data to train a single shared model with multiple task-specific layers on multiple related classification tasks to improve its generalization performance. We choose pre-trained language models (BERT-family) as the shared part of this architecture. Although they have achieved noticeable performance in different downstream NLP tasks, their performance in an MTL setting for the biomedical domain is not thoroughly investigated. In this work, we investigate the performance of BERT-family models in different MTL settings with Open-I (radiology reports) and OHSUMED (PubMed abstracts) datasets. We introduce the MTLV (Multi-Task Learning Visualizer) library for building Multi-task learning-related architectures which use existing infrastructure (e.g., Hugging Face Transformers and MLflow Tracking). Following previous work in computer vision, we clustered tasks and trained a separate model on each cluster (Grouped Multi-Task Learning (GMTL)). Contextual representation of the class labels (Tasks) and their descriptions was used by the library as features to cluster the tasks. We observed that grouping tasks for training with few models (GMTL) outperforms the MTL also GMTL is computationally more efficient than the STL setting (a separate model is trained for each task).","PeriodicalId":423462,"journal":{"name":"Proceedings of the 21st ACM Symposium on Document Engineering","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125432045","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}

引用次数: 4

Searching harsh documents 查找苛刻的文件

Proceedings of the 21st ACM Symposium on Document Engineering Pub Date : 2021-08-16 DOI: 10.1145/3469096.3469864

O. Frieder

引用次数: 0

Shock wave: a graph layout algorithm for text analyzing 冲击波:一种用于文本分析的图形布局算法

Proceedings of the 21st ACM Symposium on Document Engineering Pub Date : 2021-08-16 DOI: 10.1145/3469096.3474925

Maxime Cauz, Julien Albert, Anne Wallemacq, Isabelle Linden, Bruno Dumas

引用次数: 2

Ordering sentences and paragraphs with pre-trained encoder-decoder transformers and pointer ensembles 排序句子和段落与预先训练的编码器-解码器变压器和指针集成

Proceedings of the 21st ACM Symposium on Document Engineering Pub Date : 2021-08-16 DOI: 10.1145/3469096.3469874

Rémi Calizzano, Malte Ostendorff, G. Rehm

{"title":"Ordering sentences and paragraphs with pre-trained encoder-decoder transformers and pointer ensembles","authors":"Rémi Calizzano, Malte Ostendorff, G. Rehm","doi":"10.1145/3469096.3469874","DOIUrl":"https://doi.org/10.1145/3469096.3469874","url":null,"abstract":"Passage ordering aims to maximise discourse coherence in document generation or document modification tasks such as summarisation or storytelling. This paper extends the passage ordering task from sentences to paragraphs, i.e., passages with multiple sentences. Increasing the passage length increases the task's difficulty. To account for this, we propose the combination of a pre-trained encoder-decoder Transformer model, namely BART, with variations of pointer networks. We empirically evaluate the proposed models for sentence and paragraph ordering. Our best model outperforms previous state of the art methods by 0.057 Kendall's Tau on one of three sentence ordering benchmarks (arXiv, VIST, ROC-Story). For paragraph ordering, we construct two novel datasets from Wikipedia and CNN-DailyMail on which we achieve 0.67 and 0.47 Kendall's Tau. The best model variation utilises multiple pointer networks in an ensemble-like fashion. We hypothesise that the use of multiple pointers better reflects the multitude of possible orders of paragraphs in more complex texts. Our code, data, and models are publicly available1.","PeriodicalId":423462,"journal":{"name":"Proceedings of the 21st ACM Symposium on Document Engineering","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134117076","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}

引用次数: 5