A major challenge in fine-tuning deep learning models for automatic summarization is the need for large domain specific datasets. One of the barriers to curating such data from resources like online publications is navigating the license regulations applicable to their re-use, especially for commercial purposes. As a result, despite the availability of several business journals there are no large scale datasets for summarizing business documents. In this work, we introduce Open4Business(O4B),a dataset of 17,458 open access business articles and their reference summaries. The dataset introduces a new challenge for summarization in the business domain, requiring highly abstractive and more concise summaries as compared to other existing datasets. Additionally, we evaluate existing models on it and consequently show that models trained on O4B and a 7x larger non-open access dataset achieve comparable performance on summarization. We release the dataset, along with the code which can be leveraged to similarly gather data for multiple domains.
Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication. While machine learning problems related to Document Information Extraction (IE) have been studied for decades, many common problem definitions and benchmarks do not reflect domain-specific aspects and practical needs for automating B2B document communication. We review the landscape of Document IE problems, datasets and benchmarks. We highlight the practical aspects missing in the common definitions and define the Key Information Localization and Extraction (KILE) and Lin…
Automatic document summarization aims to produce a concise summary covering the input document's salient information. Within a report document, the salient information can be scattered in the textual and non-textual content. However, existing document summarization datasets and methods usually focus on the text and filter out the non-textual content. Missing tabular data can limit produced summaries' informativeness, especially when summaries require covering quantitative descriptions of critical metrics in tables. Existing datasets and methods cannot meet the requirements of summarizing long …
Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Salesforce AI Research（Salesforce人工智能研究部门）
KH-FUNSD: A Hierarchical and Fine-Grained Layout Analysis Dataset for Low-Resource Khmer Business Document
National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP) University of Science and Technology of China（国家语信息处理语音工程研究中心（NERC-SLIP）大学科学技术大学）
Writing a survey paper on one research topic usually needs to cover the salient content from numerous related papers, which can be modeled as a multi-document summarization (MDS) task. Existing MDS datasets usually focus on producing the structureless summary covering a few input documents. Meanwhile, previous structured summary generation works focus on summarizing a single document into a multi-section summary. These existing datasets and methods cannot meet the requirements of summarizing numerous academic papers into a structured summary. To deal with the scarcity of available data, we pro…
Business Process Management (BPM) is the discipline which is responsible for management of discovering, analyzing, redesigning, monitoring, and controlling business processes. One of the most crucial tasks of BPM is discovering and modelling business processes from text documents. In this paper, we present our system that resolves an end-to-end problem consisting of 1) recognizing conditional sentences from technical documents, 2) finding boundaries to extract conditional and resultant clauses from each conditional sentence, and 3) categorizing resultant clause as Action or Consequence which l…
A primary objective of news articles is to establish the factual record for an event, frequently achieved by conveying both the details of the specified event (i.e., the 5 Ws; Who, What, Where, When and Why regarding the event) and how people reacted to it (i.e., reported statements). However, existing work on news summarization almost exclusively focuses on the event details. In this work, we propose the novel task of summarizing the reactions of different speakers, as expressed by their reported statements, to a given event. To this end, we create a new multi-document summarization benchmark…
Computer Science and Artificial Intelligence Lab, MIT（麻省理工学院计算机科学与人工智能实验室）；ASAPP, Inc.（ASAPP公司）
We introduce \emph{Nutri-bullets}, a multi-document summarization task for health and nutrition. First, we present two datasets of food and health summaries from multiple scientific studies. Furthermore, we propose a novel \emph{extract-compose} model to solve the problem in the regime of limited parallel data. We explicitly select key spans from several abstracts using a policy network, followed by composing the selected spans to present a summary via a task specific language model. Compared to state-of-the-art methods, our approach leads to more faithful, relevant and diverse summarization -…
Salesforce Research（赛富时研究院）；Columbia University（哥伦比亚大学）；Yale University（耶鲁大学）；Stanford University（斯坦福大学）；University of Pennsylvania（宾夕法尼亚大学）；Duke University（杜克大学）
This paper introduces the shared task of summarizing documents in several creative domains, namely literary texts, movie scripts, and television scripts. Summarizing these creative documents requires making complex literary interpretations, as well as understanding non-trivial temporal dependencies in texts containing varied styles of plot development and narrative structure. This poses unique challenges and is yet underexplored for text summarization systems. In this shared task, we introduce four sub-tasks and their corresponding datasets, focusing on summarizing books, movie scripts, primet…
Multi-domain Multi-modal Document Classification Benchmark with a Multi-level Taxonomy
Beijing Information Science and Technology University（北京信息科学与技术大学）；Alibaba Group（阿里巴巴集团）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东人工智能与数字经济实验室（深圳））；Guangzhou University（广州大学）；Zhejiang Lab（浙江实验室）
We present an approach for summarization from multiple documents which report on events that evolve through time, taking into account the different document sources. We distinguish the evolution of an event into linear and non-linear. According to our approach, each document is represented by a collection of messages which are then used in order to instantiate the cross-document relations that determine the summary content. The paper presents the summarization system that implements this approach through a case study on linear evolution.
In this paper we present a fresh look at the problem of summarizing evolving events from multiple sources. After a discussion concerning the nature of evolving events we introduce a distinction between linearly and non-linearly evolving events. We present then a general methodology for the automatic creation of summaries from evolving events. At its heart lie the notions of Synchronic and Diachronic cross-document Relations (SDRs), whose aim is the identification of similarities and differences between sources, from a synchronical and diachronical perspective. SDRs do not connect documents or …
A Mixed-Language Multi-Document News Summarization Dataset and a Graphs-Based Extract-Generate Model
Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology（昆明理工大学云南省人工智能重点实验室）
Institute of Computer Science, Heidelberg University（海德堡大学计算机科学研究所）
Traditionally, Text Simplification is treated as a monolingual translation task where sentences between source texts and their simplified counterparts are aligned for training. However, especially for longer input documents, summarizing the text (or dropping less relevant content altogether) plays an important role in the simplification process, which is currently not reflected in existing datasets. Simultaneously, resources for non-English languages are scarce in general and prohibitive for training new solutions. To tackle this problem, we pose core requirements for a system that can jointly…
Methods for detecting and summarizing emergent keywords have been extensively studied since social media and microblogging activities have started to play an important role in data analysis and decision making. We present a system for monitoring emergent keywords and summarizing a document stream based on the dynamic semantic graphs of streaming documents. We introduce the notion of dynamic eigenvector centrality for ranking emergent keywords, and present an algorithm for summarizing emergent events that is based on the minimum weight set cover. We demonstrate our system with an analysis of st…
Techniques for automatically extracting important content elements from business documents such as contracts, statements, and filings have the potential to make business operations more efficient. This problem can be formulated as a sequence labeling task, and we demonstrate the adaption of BERT to two types of business documents: regulatory filings and property lease agreements. There are aspects of this problem that make it easier than "standard" information extraction tasks and other aspects that make it more difficult, but on balance we find that modest amounts of annotated data (less than…
Summarizing text-rich documents has been long studied in the literature, but most of the existing efforts have been made to summarize a static and predefined multi-document set. With the rapid development of online platforms for generating and distributing text-rich documents, there arises an urgent need for continuously summarizing dynamically evolving multi-document sets where the composition of documents and sets is changing over time. This is especially challenging as the summarization should be not only effective in incorporating relevant, novel, and distinctive information from each conc…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
Understanding large, structured documents like scholarly articles, requests for proposals or business reports is a complex and difficult task. It involves discovering a document's overall purpose and subject(s), understanding the function and meaning of its sections and subsections, and extracting low level entities and facts about them. In this research, we present a deep learning based document ontology to capture the general purpose semantic structure and domain specific semantic concepts from a large number of academic articles and business documents. The ontology is able to describe diffe…
Northeastern University（东北大学）；King’s College London（伦敦国王学院）
We present TrialsSummarizer, a system that aims to automatically summarize evidence presented in the set of randomized controlled trials most relevant to a given query. Building on prior work, the system retrieves trial publications matching a query specifying a combination of condition, intervention(s), and outcome(s), and ranks these according to sample size and estimated study quality. The top-k such studies are passed through a neural multi-document summarization system, yielding a synopsis of these trials. We consider two architectures: A standard sequence-to-sequence model based on BART …
In this paper, we propose a novel one-shot template-matching algorithm to automatically capture data from business documents with an aim to minimize manual data entry. Given one annotated document, our algorithm can automatically extract similar data from other documents having the same format. Based on a set of engineered visual and textual features, our method is invariant to changes in position and value. Experiments on a dataset of 595 real invoices demonstrate 86.4% accuracy.
IIT Kharagpur（印度理工学院卡哈拉格普尔分校）；L3S Research Center（L3S研究中心）
Automatic summarization of legal case documents is an important and practical challenge. Apart from many domain-independent text summarization algorithms that can be used for this purpose, several algorithms have been developed specifically for summarizing legal case documents. However, most of the existing algorithms do not systematically incorporate domain knowledge that specifies what information should ideally be present in a legal case document summary. To address this gap, we propose an unsupervised summarization algorithm DELSumm which is designed to systematically incorporate guideline…
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…
We present CAiRE-COVID, a real-time question answering (QA) and multi-document summarization system, which won one of the 10 tasks in the Kaggle COVID-19 Open Research Dataset Challenge, judged by medical experts. Our system aims to tackle the recent challenge of mining the numerous scientific articles being published on COVID-19 by answering high priority questions from the community and summarizing salient question-related information. It combines information extraction with state-of-the-art QA and query-focused multi-document summarization techniques, selecting and highlighting evidence sni…
Jožef Stefan International Postgraduate School（约瑟夫·斯特凡国际研究生院）；Jožef Stefan Institute（约瑟夫·斯特凡研究所）；Usher Institute, Medical School, University of Edinburgh（爱丁堡大学医学院厄舍研究所）
Keyword extraction is used for summarizing the content of a document and supports efficient document retrieval, and is as such an indispensable part of modern text-based systems. We explore how load centrality, a graph-theoretic measure applied to graphs derived from a given text can be used to efficiently identify and rank keywords. Introducing meta vertices (aggregates of existing vertices) and systematic redundancy filters, the proposed method performs on par with state-of-the-art for the keyword extraction task on 14 diverse datasets. The proposed method is unsupervised, interpretable and …
Automating information extraction from form-like documents at scale is a pressing need due to its potential impact on automating business workflows across many industries like financial services, insurance, and healthcare. The key challenge is that form-like documents in these business workflows can be laid out in virtually infinitely many ways; hence, a good solution to this problem should generalize to documents with unseen layouts and languages. A solution to this problem requires a holistic understanding of both the textual segments and the visual cues within a document, which is non-trivi…
