This paper presents a comprehensive survey of research works on the topic of form understanding in the context of scanned documents. We delve into recent advancements and breakthroughs in the field, highlighting the significance of language models and transformers in solving this challenging task. Our research methodology involves an in-depth analysis of popular documents and forms of understanding of trends over the last decade, enabling us to offer valuable insights into the evolution of this domain. Focusing on cutting-edge models, we showcase how transformers have propelled the field forward, revolutionizing form-understanding techniques. Our exploration includes an extensive examination of state-of-the-art language models designed to effectively tackle the complexities of noisy scanned documents. Furthermore, we present an overview of the latest and most relevant datasets, which serve as essential benchmarks for evaluating the performance of selected models. By comparing and contrasting the capabilities of these models, we aim to provide researchers and practitioners with useful guidance in choosing the most suitable solutions for their specific form understanding tasks.
Automatic table detection in PDF documents has achieved a great success but tabular data extraction are still challenging due to the integrity and noise issues in detected table areas. The accurate data extraction is extremely crucial in finance area. Inspired by this, the aim of this research is proposing an automated table detection and tabular data extraction from financial PDF documents. We proposed a method that consists of three main processes, which are detecting table areas with a Faster R-CNN (Region-based Convolutional Neural Network) model with Feature Pyramid Network (FPN) on each …
Virginia Polytechnic Institute and State University（弗吉尼亚理工学院暨州立大学）；Old Dominion University（奥多明尼昂大学）
We focus on electronic theses and dissertations (ETDs), aiming to improve access and expand their utility, since more than 6 million are publicly available, and they constitute an important corpus to aid research and education across disciplines. The corpus is growing as new born-digital documents are included, and since millions of older theses and dissertations have been converted to digital form to be disseminated electronically in institutional repositories. In ETDs, as with other scholarly works, figures and tables can communicate a large amount of information in a concise way. Although m…
German Research Center for Artificial Intelligence (DFKI GmbH)（德国人工智能研究中心）；Technische Universität Kaiserslautern（凯泽斯劳滕工业大学）；Osaka Prefecture University（大阪府立大学）
The contribution of this paper is fourfold. The first contribution is a novel, generic method for automatic ground truth generation of camera-captured document images (books, magazines, articles, invoices, etc.). It enables us to build large-scale (i.e., millions of images) labeled camera-captured/scanned documents datasets, without any human intervention. The method is generic, language independent and can be used for generation of labeled documents datasets (both scanned and cameracaptured) in any cursive and non-cursive language, e.g., English, Russian, Arabic, Urdu, etc. To assess the effe…
With the widespread use of mobile phones and scanners to photograph and upload documents, the need for extracting the information trapped in unstructured document images such as retail receipts, insurance claim forms and financial invoices is becoming more acute. A major hurdle to this objective is that these images often contain information in the form of tables and extracting data from tabular sub-images presents a unique set of challenges. This includes accurate detection of the tabular region within an image, and subsequently detecting and extracting information from the rows and columns o…
Information extraction (IE) from documents is an intensive area of research with a large set of industrial applications. Current state-of-the-art methods focus on scanned documents with approaches combining computer vision, natural language processing and layout representation. We propose to challenge the usage of computer vision in the case where both token style and visual representation are available (i.e native PDF documents). Our experiments on three real-world complex datasets demonstrate that using token style attributes based embedding instead of a raw visual embedding in LayoutLM mode…
University of Science and Technology of China（中国科学技术大学）；iFLYTEK Research（科大讯飞研究院）
The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on splitting the boundary of each element in a single document page, neglecting the reconstruction of semantic structure in multi-page documents. This paper introduces hierarchical reconstruction of document structures as a novel task suitable for NLP and CV fields. To better evaluate the system performance on the new task, we built a large-scale dataset named HRDoc, which consists of 2,500 multi-page documents with nearly 2…
The possibility of carrying out a meaningful forensics analysis on printed and scanned images plays a major role in many applications. First of all, printed documents are often associated with criminal activities, such as terrorist plans, child pornography pictures, and even fake packages. Additionally, printing and scanning can be used to hide the traces of image manipulation or the synthetic nature of images, since the artifacts commonly found in manipulated and synthetic images are gone after the images are printed and scanned. A problem hindering research in this area is the lack of large …
Unstructured documents serving as external knowledge of the dialogues help to generate more informative responses. Previous research focused on knowledge selection (KS) in the document with dialogue. However, dialogue history that is not related to the current dialogue may introduce noise in the KS processing. In this paper, we propose a Compare Aggregate Transformer (CAT) to jointly denoise the dialogue context and aggregate the document information for response generation. We designed two different comparison mechanisms to reduce noise (before and during decoding). In addition, we propose tw…
High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer
School of Computer Science and Engineering, Huizhou University（惠州学院计算机科学与工程学院）；Faculty of Science and Technology, University of Macau（澳门大学科技学院）；School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；School of Electronic and Communication Engineering, Shenzhen Polytechnic University（深圳职业技术学院电子与通信工程学院）
DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarization
Optiks Innovations Pvt. Ltd（奥普蒂克斯创新私人有限公司）；Alipurduar Government Engineering and Management College（阿里布尔杜阿尔政府工程与管理学院）；Chongqing College of Mobile Communication（重庆移通学院）；Indian Statistical Institute（印度统计研究所）；Nanyang Technological University（南洋理工大学）
Institute for Language, Cognition and Computation（语言、认知与计算研究所）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
In this paper, we develop a neural summarization model which can effectively process multiple input documents and distill Transformer architecture with the ability to encode documents in a hierarchical manner. We represent cross-document relationships via an attention mechanism which allows to share information as opposed to simply concatenating text spans and processing them as a flat sequence. Our model learns latent dependencies among textual units, but can also take advantage of explicit graph representations focusing on similarity or discourse relations. Empirical results on the WikiSum d…
Deep learning-based NLP Data Pipeline for EHR Scanned Document Information Extraction
Division of Pulmonary, Critical Care and Sleep Medicine, Department of Internal Medicine, University of Texas Medical Branch（德克萨斯大学医学分部内科学系肺、重症监护与睡眠医学部）；School of Biomedical Informatics, University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心生物医学信息学学院）；Center for Outcomes Research, Houston Methodist（休斯顿卫理公会医院结果研究中心）
Information extraction from documents is a ubiquitous first step in many business applications. During this step, the entries of various fields must first be read from the images of scanned documents before being further processed and inserted into the corresponding databases. While many different methods have been developed over the past years in order to automate the above extraction step, they all share the requirement of bounding-box or text segment annotations of their training documents. In this work we present DocReader, an end-to-end neural-network-based information extraction solution…
School of Biomedical Informatics, The University of Texas Health Science Center（德克萨斯大学健康科学中心生物医学信息学院）
We present a Three-level Hierarchical Transformer Network (3-level-HTN) for modeling long-term dependencies across clinical notes for the purpose of patient-level prediction. The network is equipped with three levels of Transformer-based encoders to learn progressively from words to sentences, sentences to notes, and finally notes to patients. The first level from word to sentence directly applies a pre-trained BERT model as a fully trainable component. While the second and third levels both implement a stack of transformer-based encoders, before the final patient representation is fed into a …
This paper presents a new training dataset for automatic genre identification GINCO, which is based on 1,125 crawled Slovenian web documents that consist of 650 thousand words. Each document was manually annotated for genre with a new annotation schema that builds upon existing schemata, having primarily clarity of labels and inter-annotator agreement in mind. The dataset consists of various challenges related to web-based data, such as machine translated content, encoding errors, multiple contents presented in one document etc., enabling evaluation of classifiers in realistic conditions. The …
While storing invoice content as metadata to avoid paper document processing may be the future trend, almost all of daily issued invoices are still printed on paper or generated in digital formats such as PDFs. In this paper, we introduce the OCRMiner system for information extraction from scanned document images which is based on text analysis techniques in combination with layout features to extract indexing metadata of (semi-)structured documents. The system is designed to process the document in a similar way a human reader uses, i.e. to employ different layout and text attributes in a coo…
Harbin Institute of Technology（哈尔滨工业大学）；Beihang University（北京航空航天大学）；Microsoft Research Asia（微软亚洲研究院）
Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the widespread use of pre-training models for NLP applications, they almost exclusively focus on text-level manipulation, while neglecting layout and style information that is vital for document image understanding. In this paper, we propose the \textbf{LayoutLM} to jointly model interactions between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding tasks such as information extraction from scanned…
Forms are a widespread type of template-based document used in a great variety of fields including, among others, administration, medicine, finance, or insurance. The automatic extraction of the information included in these documents is greatly demanded due to the increasing volume of forms that are generated in a daily basis. However, this is not a straightforward task when working with scanned forms because of the great diversity of templates with different location of form entities, and the quality of the scanned documents. In this context, there is a feature that is shared by all forms: t…
We address the challenge of extracting structured information from business documents without detailed annotations. We propose Deep Conditional Probabilistic Context Free Grammars (DeepCPCFG) to parse two-dimensional complex documents and use Recursive Neural Networks to create an end-to-end system for finding the most probable parse that represents the structured information to be extracted. This system is trained end-to-end with scanned documents as input and only relational-records as labels. The relational-records are extracted from existing databases avoiding the cost of annotating docume…
Indian Institute of Information Technology Allahabad（印度理工学院阿拉哈巴德分校）
In today's technological era, document images play an important and integral part in our day to day life, and specifically with the surge of Covid-19, digitally scanned documents have become key source of communication, thus avoiding any sort of infection through physical contact. Storage and transmission of scanned document images is a very memory intensive task, hence compression techniques are being used to reduce the image size before archival and transmission. To extract information or to operate on the compressed images, we have two ways of doing it. The first way is to decompress the im…
Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding~(VDU). While various vision-language pre-training objectives are studied in existing solutions, the document textline, as an intrinsic granularity in VDU, has seldom been explored so far. A document textline usually contains words that are spatially and semantically correlated, which can be easily obtained from OCR engines. In this paper, we propose Wukong-Reader, trained with new pre-training objectives to leverage the structural knowledge nested in document…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Transformer is important for text modeling. However, it has difficulty in handling long documents due to the quadratic complexity with input text length. In order to handle this problem, we propose a hierarchical interactive Transformer (Hi-Transformer) for efficient and effective long document modeling. Hi-Transformer models documents in a hierarchical way, i.e., first learns sentence representations and then learns document representations. It can effectively reduce the complexity and meanwhile capture global document context in the modeling of each sentence. More specifically, we first use …
InstaDeep；Digital Research Center of Sfax（斯法克斯数字研究中心）
The extraction of relevant information carried out by named entities in handwriting documents is still a challenging task. Unlike traditional information extraction approaches that usually face text transcription and named entity recognition as separate subsequent tasks, we propose in this paper an end-to-end transformer-based approach to jointly perform these two tasks. The proposed approach operates at the paragraph level, which brings two main benefits. First, it allows the model to avoid unrecoverable early errors due to line segmentation. Second, it allows the model to exploit larger bi-d…
CSIRO Data61（澳大利亚联邦科学与工业研究组织Data61）；University of Copenhagen（哥本哈根大学）；Pioneer Centre for AI（人工智能先锋中心）
The recent literature in text classification is biased towards short text sequences (e.g., sentences or paragraphs). In real-world applications, multi-page multi-paragraph documents are common and they cannot be efficiently encoded by vanilla Transformer-based models. We compare different Transformer-based Long Document Classification (TrLDC) approaches that aim to mitigate the computational overhead of vanilla transformers to encode much longer text, namely sparse attention and hierarchical encoding methods. We examine several aspects of sparse attention (e.g., size of local attention window,…
Shanghai Jiao Tong University（上海交通大学）；Microsoft Research Asia（微软亚洲研究院）
Multimodal pre-training with text, layout, and image has made significant progress for Visually Rich Document Understanding (VRDU), especially the fixed-layout documents such as scanned document images. While, there are still a large number of digital documents where the layout information is not fixed and needs to be interactively and dynamically rendered for visualization, making existing layout-based pre-training approaches not easy to apply. In this paper, we propose MarkupLM for document understanding tasks with markup languages as the backbone, such as HTML/XML-based documents, where tex…
University of Zurich（苏黎世大学）；Walter Benjamin Kolleg（瓦尔特·本雅明学院）；University of Bern（伯尔尼大学）
We apply the TrOCR framework to real-world, historical manuscripts and show that TrOCR per se is a strong model, ideal for transfer learning. TrOCR has been trained on English only, but it can adapt to other languages that use the Latin alphabet fairly easily and with little training material. We compare TrOCR against a SOTA HTR framework (Transkribus) and show that it can beat such systems. This finding is essential since Transkribus performs best when it has access to baseline information, which is not needed at all to fine-tune TrOCR.
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Sogou Inc.（搜狗公司）；Soochow University（苏州大学）
Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer still remains a challenge. In this work, we extend the Transformer model with a new context encoder to represent document-level context, which is then incorporated into the original encoder and decoder. As large-scale document-level parallel corpora are usually not available, we introduce a two-step training method to take full advantage of abundant sentence-l…
Directly training a document-to-document (Doc2Doc) neural machine translation (NMT) via Transformer from scratch, especially on small datasets usually fails to converge. Our dedicated probing tasks show that 1) both the absolute position and relative position information gets gradually weakened or even vanished once it reaches the upper encoder layers, and 2) the vanishing of absolute position information in encoder output causes the training failure of Doc2Doc NMT. To alleviate this problem, we propose a position-aware Transformer (P-Transformer) to enhance both the absolute and relative posi…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Northeastern University（东北大学）；Huazhong University of Science and Technology（华中科技大学）；Tencent Inc（腾讯公司）
Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document. Obviously, document knowledge plays a critical role in Document Grounded Conversations, while existing dialogue models do not exploit this kind of knowledge effectively enough. In this paper, we propose a novel Transformer-based architecture for multi-turn document grounded conversations. In particular, we devise an Incremental Transformer to encode multi-turn utterances along with knowledge in related documents. Motivated by the human cognitive process, we design a two…
Recent efforts of multimodal Transformers have improved Visually Rich Document Understanding (VrDU) tasks via incorporating visual and textual information. However, existing approaches mainly focus on fine-grained elements such as words and document image patches, making it hard for them to learn from coarse-grained elements, including natural lexical units like phrases and salient visual regions like prominent image regions. In this paper, we attach more importance to coarse-grained elements containing high-density information and consistent semantics, which are valuable for document understa…
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）
Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level training objectives and do not leverage information on inter-document relatedness, which limits their document-level representation power. For applications on scientific documents, such as classification and recommendation, the embeddings power strong performance on end tasks. We propose SPECTER, a new method to generate document-level embedding of scientific…
University of Arizona（亚利桑那大学）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）；University of Wisconsin–Madison（威斯康星大学麦迪逊分校）；Loyola University Chicago（芝加哥洛约拉大学）
Automatic phenotyping is a task of identifying cohorts of patients that match a predefined set of criteria. Phenotyping typically involves classifying long clinical documents that contain thousands of tokens. At the same time, recent state-of-art transformer-based pre-trained language models limit the input to a few hundred tokens (e.g. 512 tokens for BERT). We evaluate several strategies for incorporating pre-trained sentence encoders into document-level representations of clinical text, and find that hierarchical transformers without pre-training are competitive with task pre-trained models.
Virginia Tech（弗吉尼亚理工大学）；InterDigital（InterDigital公司）
Recent advances in the area of long document matching have primarily focused on using transformer-based models for long document encoding and matching. There are two primary challenges associated with these models. Firstly, the performance gain provided by transformer-based models comes at a steep cost - both in terms of the required training time and the resource (memory and energy) consumption. The second major limitation is their inability to handle more than a pre-defined input token length at a time. In this work, we empirically demonstrate the effectiveness of simple neural models (such …
Extractive summarization for long documents is challenging due to the extended structured input context. The long-distance sentence dependency hinders cross-sentence relations modeling, the critical step of extractive summarization. This paper proposes HEGEL, a hypergraph neural network for long document summarization by capturing high-order cross-sentence relations. HEGEL updates and learns effective sentence representations with hypergraph transformer layers and fuses different types of sentence dependencies, including latent topics, keywords coreference, and section structure. We validate H…
University of Copenhagen（哥本哈根大学）；CSIRO Data61（澳大利亚联邦科学与工业研究组织Data61）；Athens University of Economics and Business（雅典经济与商业大学）；Pioneer Centre for AI（人工智能先锋中心）
Non-hierarchical sparse attention Transformer-based models, such as Longformer and Big Bird, are popular approaches to working with long documents. There are clear benefits to these approaches compared to the original Transformer in terms of efficiency, but Hierarchical Attention Transformer (HAT) models are a vastly understudied alternative. We develop and release fully pre-trained HAT models that use segment-wise followed by cross-segment encoders and compare them with Longformer models and partially pre-trained HATs. In several long document downstream classification tasks, our best HAT mod…
Transformers are not suited for processing long documents, due to their quadratically increasing memory and time consumption. Simply truncating a long document or applying the sparse attention mechanism will incur the context fragmentation problem or lead to an inferior modeling capability against comparable model sizes. In this paper, we propose ERNIE-Doc, a document-level language pretraining model based on Recurrence Transformers. Two well-designed techniques, namely the retrospective feed mechanism and the enhanced recurrence mechanism, enable ERNIE-Doc, which has a much longer effective c…
South China University of Technology（华南理工大学）；Peng Cheng Laboratory（鹏城实验室）；IntSig Information Co., Ltd（合合信息科技股份有限公司）
Structured document understanding has attracted considerable attention and made significant progress recently, owing to its crucial role in intelligent document processing. However, most existing related models can only deal with the document data of specific language(s) (typically English) included in the pre-training collection, which is extremely limited. To address this issue, we propose a simple yet effective Language-independent Layout Transformer (LiLT) for structured document understanding. LiLT can be pre-trained on the structured documents of a single language and then directly fine-…
Charles University（查理大学）；Faculty of Mathematics and Physics（数学与物理学院）；Institute of Formal and Applied Linguistics（形式与应用语言学研究所）
We describe our NMT systems submitted to the WMT19 shared task in English-Czech news translation. Our systems are based on the Transformer model implemented in either Tensor2Tensor (T2T) or Marian framework. We aimed at improving the adequacy and coherence of translated documents by enlarging the context of the source and target. Instead of translating each sentence independently, we split the document into possibly overlapping multi-sentence segments. In case of the T2T implementation, this "document-level"-trained system achieves a $+0.6$ BLEU improvement ($p<0.05$) relative to the same syst…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Microsoft Research AI（微软研究院人工智能部门）
The computing cost of transformer self-attention often necessitates breaking long documents to fit in pretrained models in document ranking tasks. In this paper, we design Query-Directed Sparse attention that induces IR-axiomatic structures in transformer self-attention. Our model, QDS-Transformer, enforces the principle properties desired in ranking: local contextualization, hierarchical representation, and query-oriented proximity matching, while it also enjoys efficiency from sparsity. Experiments on one fully supervised and three few-shot TREC document ranking benchmarks demonstrate the co…
In document-level event extraction (DEE) task, event arguments always scatter across sentences (across-sentence issue) and multiple events may lie in one document (multi-event issue). In this paper, we argue that the relation information of event arguments is of great significance for addressing the above two issues, and propose a new DEE framework which can model the relation dependencies, called Relation-augmented Document-level Event Extraction (ReDEE). More specifically, this framework features a novel and tailored transformer, named as Relation-augmented Attention Transformer (RAAT). RAAT…
We revisit the classic problem of document-level role-filler entity extraction (REE) for template filling. We argue that sentence-level approaches are ill-suited to the task and introduce a generative transformer-based encoder-decoder framework (GRIT) that is designed to model context at the document level: it can make extraction decisions across sentence boundaries; is implicitly aware of noun phrase coreference structure, and has the capacity to respect cross-role dependencies in the template structure. We evaluate our approach on the MUC-4 dataset, and show that our model performs substanti…
