Relational understanding is critical for a number of visually-rich documents (VRDs) understanding tasks. Through multi-modal pre-training, recent studies provide comprehensive contextual representations and exploit them as prior knowledge for downstream tasks. In spite of their impressive results, we observe that the widespread relational hints (e.g., relation of key/value fields on receipts) built upon contextual knowledge are not excavated yet. To mitigate this gap, we propose DocReL, a Document Relational Representation Learning framework. The major challenge of DocReL roots in the variety of relations. From the simplest pairwise relation to the complex global structure, it is infeasible to conduct supervised training due to the definition of relation varies and even conflicts in different tasks. To deal with the unpredictable definition of relations, we propose a novel contrastive learning task named Relational Consistency Modeling (RCM), which harnesses the fact that existing relations should be consistent in differently augmented positive views. RCM provides relational representations which are more compatible to the urgent need of downstream tasks, even without any knowledge about the exact definition of relation. DocReL achieves better performance on a wide variety of VRD relational understanding tasks, including table structure recognition, key information extraction and reading order detection.
Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction
School of Computer Science, Fudan University（复旦大学计算机科学学院）；School of Statistics and Data Science, Nankai University（南开大学统计与数据科学学院）；Ant Tiansuan Security Lab, Ant Group（蚂蚁集团蚂蚁天算安全实验室）
Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding. However, most existing methods lack the systematic mining and utilization of layout-centered knowledge, leading to sub-optimal performances. In this paper, we propose ERNIE-Layout, a novel document pre-training solution with layout knowledge enhancement in the whole workflow, to learn better representations that combine the features from text, layout, and image. Specifically, we first rearrange input sequences in the serialization stage, and then present a correlative pre-traini…
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…
Previous works on key information extraction from visually rich documents (VRDs) mainly focus on labeling the text within each bounding box (i.e., semantic entity), while the relations in-between are largely unexplored. In this paper, we adapt the popular dependency parsing model, the biaffine parser, to this entity relation extraction task. Being different from the original dependency parsing model which recognizes dependency relations between words, we identify relations between groups of words with layout information instead. We have compared different representations of the semantic entity…
IRIT, Université de Toulouse, CNRS（图卢兹大学 IRIT 研究所、法国国家科学研究中心）
The state-of-the-art solutions to the vocabulary mismatch in information retrieval (IR) mainly aim at leveraging either the relational semantics provided by external resources or the distributional semantics, recently investigated by deep neural approaches. Guided by the intuition that the relational semantics might improve the effectiveness of deep neural approaches, we propose the Deep Semantic Resource Inference Model (DSRIM) that relies on: 1) a representation of raw-data that models the relational semantics of text by jointly considering objects and relations expressed in a knowledge reso…
We introduce a relational graph neural network with bi-directional attention mechanism and hierarchical representation learning for open-domain question answering task. Our model can learn contextual representation by jointly learning and updating the query, knowledge graph, and document representations. The experiments suggest that our model achieves state-of-the-art on the WebQuestionsSP benchmark.
Document-level relation extraction (RE) aims to extract the relations between entities from the input document that usually containing many difficultly-predicted entity pairs whose relations can only be predicted through relational inference. Existing methods usually directly predict the relations of all entity pairs of input document in a one-pass manner, ignoring the fact that predictions of some entity pairs heavily depend on the predicted results of other pairs. To deal with this issue, in this paper, we propose a novel document-level RE model with iterative inference. Our model is mainly …
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…
Nanyang Technological University（南洋理工大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）
Open Information Extraction (OpenIE) aims to extract structured relational tuples (subject, relation, object) from sentences and plays critical roles for many downstream NLP applications. Existing solutions perform extraction at sentence level, without referring to any additional contextual information. In reality, however, a sentence typically exists as part of a document rather than standalone; we often need to access relevant contextual information around the sentence before we can accurately interpret it. As there is no document-level context-aware OpenIE dataset available, we manually ann…
Purdue University（普渡大学）；American University of Beirut（贝鲁特美国大学）
Rule-based techniques to extract relational entities from documents allow users to specify desired entities with natural language questions, finite state automata, regular expressions and structured query language. They require linguistic and programming expertise and lack support for Arabic morphological analysis. We present a morphology-based entity and relational entity extraction framework for Arabic (MERF). MERF requires basic knowledge of linguistic features and regular expressions, and provides the ability to interactively specify Arabic morphological and synonymity features, tag types …
Indiana University（印第安纳大学）；Swarthmore College（斯沃斯莫尔学院）；University of Wisconsin – Madison（威斯康星大学麦迪逊分校）
We consider the task of KBP slot filling -- extracting relation information from newswire documents for knowledge base construction. We present our pipeline, which employs Relational Dependency Networks (RDNs) to learn linguistic patterns for relation extraction. Additionally, we demonstrate how several components such as weak supervision, word2vec features, joint learning and the use of human advice, can be incorporated in this relational framework. We evaluate the different components in the benchmark KBP 2015 task and show that RDNs effectively model a diverse set of features and perform co…
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…
A key bottleneck in building automatic extraction models for visually rich documents like invoices is the cost of acquiring the several thousand high-quality labeled documents that are needed to train a model with acceptable accuracy. We propose Selective Labeling to simplify the labeling task to provide "yes/no" labels for candidate extractions predicted by a model trained on partially labeled documents. We combine this with a custom active learning strategy to find the predictions that the model is most uncertain about. We show through experiments on document types drawn from 3 different dom…
We introduce RelNet: a new model for relational reasoning. RelNet is a memory augmented neural network which models entities as abstract memory slots and is equipped with an additional relational memory which models relations between all memory pairs. The model thus builds an abstract knowledge graph on the entities and relations present in a document which can then be used to answer questions about the document. It is trained end-to-end: only supervision to the model is in the form of correct answers to the questions. We test the model on the 20 bAbI question-answering tasks with 10k examples…
Recent advancements in the area of Computer Vision with state-of-art Neural Networks has given a boost to Optical Character Recognition (OCR) accuracies. However, extracting characters/text alone is often insufficient for relevant information extraction as documents also have a visual structure that is not captured by OCR. Extracting information from tables, charts, footnotes, boxes, headings and retrieving the corresponding structured representation for the document remains a challenge and finds application in a large number of real-world use cases. In this paper, we propose a novel enterpris…
Microsoft Research Asia（微软亚洲研究院）；Microsoft Azure AI（微软Azure人工智能）
Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. To accurately evaluate LayoutXLM, we also introduce a multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chin…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
This paper presents a new task of predicting the coverage of a text document for relation extraction (RE): does the document contain many relational tuples for a given entity? Coverage predictions are useful in selecting the best documents for knowledge base construction with large input corpora. To study this problem, we present a dataset of 31,366 diverse documents for 520 entities. We analyze the correlation of document coverage with features like length, entity mention frequency, Alexa rank, language complexity and information retrieval scores. Each of these features has only moderate pred…
Many business workflows require extracting important fields from form-like documents (e.g. bank statements, bills of lading, purchase orders, etc.). Recent techniques for automating this task work well only when trained with large datasets. In this work we propose a novel data augmentation technique to improve performance when training data is scarce, e.g. 10-250 documents. Our technique, which we call FieldSwap, works by swapping out the key phrases of a source field with the key phrases of a target field to generate new synthetic examples of the target field for use in training. We demonstra…
Harbin Institute of Technology（哈尔滨工业大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft Azure AI（微软 Azure AI）；Soochow University（苏州大学）
Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents. We propose LayoutLMv2 architecture with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. Specifically, with a two-stream multi-modal Transformer encoder, LayoutLMv2 uses not only the existing masked visual-language modeling task but also the new text-image alignment and text-image matching tasks, which make …
Zhejiang University（浙江大学）；AZFT Joint Lab for Knowledge Engine（AZFT知识引擎联合实验室）；Hangzhou Innovation Center, Zhejiang University（浙江大学杭州国际科创中心）；Alibaba Group（阿里巴巴集团）
Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among relational triples. This paper approaches the problem by predicting an entity-level relation matrix to capture local and global information, parallel to the semantic segmentation task in computer vision. Herein, we propose a Document U-shaped Network for document-level relation extraction. Specifically, we leverage an encoder module to capture the context i…
RV College of Engineering（RV工程学院）；IBM Research（IBM研究院）；IIT Guwahati（印度理工学院古瓦哈蒂分校）
Ontologies comprising of concepts, their attributes, and relationships are used in many knowledge based AI systems. While there have been efforts towards populating domain specific ontologies, we examine the role of document structure in learning ontological relationships between concepts in any document corpus. Inspired by ideas from hypernym discovery and explainability, our method performs about 15 points more accurate than a stand-alone R-GCN model for this task.
Recently, various multimodal networks for Visually-Rich Document Understanding(VRDU) have been proposed, showing the promotion of transformers by integrating visual and layout information with the text embeddings. However, most existing approaches utilize the position embeddings to incorporate the sequence information, neglecting the noisy improper reading order obtained by OCR tools. In this paper, we propose a robust layout-aware multimodal network named XYLayoutLM to capture and leverage rich layout information from proper reading orders produced by our Augmented XY Cut. Moreover, a Dilated…
Document-level Event Causality Identification (DECI) aims to identify causal relations between event pairs in a document. It poses a great challenge of across-sentence reasoning without clear causal indicators. In this paper, we propose a novel Event Relational Graph TransfOrmer (ERGO) framework for DECI, which improves existing state-of-the-art (SOTA) methods upon two aspects. First, we formulate DECI as a node classification problem by constructing an event relational graph, without the needs of prior knowledge or tools. Second, ERGO seamlessly integrates event-pair relation classification a…
Many business documents processed in modern NLP and IR pipelines are visually rich: in addition to text, their semantics can also be captured by visual traits such as layout, format, and fonts. We study the problem of information extraction from visually rich documents (VRDs) and present a model that combines the power of large pre-trained language models and graph neural networks to efficiently encode both textual and visual information in business documents. We further introduce new fine-tuning objectives to improve in-domain unsupervised fine-tuning to better utilize large amount of unlabel…
Deep reading models for question-answering have demonstrated promising performance over the last couple of years. However current systems tend to learn how to cleverly extract a span of the source document, based on its similarity with the question, instead of seeking for the appropriate answer. Indeed, a reading machine should be able to detect relevant passages in a document regarding a question, but more importantly, it should be able to reason over the important pieces of the document in order to produce an answer when it is required. To motivate this purpose, we present ReviewQA, a questi…
