检索结果-内蒙古大学图书馆

document structure model for survey generation using neural network

Frontiers of Computer Science 2021年第4期15卷 73-82页

作者： Huiyan XU Zhongqing WANG Yifei ZHANG Xiaolan WENG ZhijianWANG Guodong ZHOU College of Computer and Information Hohai UniversityNanjing 210098China School of Computer Science and Technology Huaiyin Normal UniversityHuai’an 223300China Natural Language Processing Lab Soochow UniversitySuzhou 215006China

Survey generation aims to generate a summary from a scientific topic based on related *** structure of papers deeply influences the generative process of survey,especially the relationships between sentence and sentence,paragraph and *** principle,the structure of paper can influence the quality of the ***,we employ the structure of paper to leverage contextual information among sentences in paragraphs to generate a survey for *** particular,we present a neural document structure model for survey *** take paragraphs as units,and model sentences in paragraphs,we then employ a hierarchical model to learn structure among sentences,which can be used to select important and informative sentences to generate *** evaluate our model on scientific document data *** experimental results show that our model is effective,and the generated survey is informative and readable.

关键词： survey generation contextual information document structure

来源：评论

学校读者我要写书评

暂无评论

document-level medical relation extraction via edge-oriented graph neural network based on document structure and external knowledge

引用

BMC MEDICAL INFORMATICS AND DECISION MAKING 2021年第SUPPL 7期21卷 1-10页

作者： Li, Tao Xiong, Ying Wang, Xiaolong Chen, Qingcai Tang, Buzhou Harbin Inst Technol Shenzhen Peoples R China Peng Cheng Lab Shenzhen Peoples R China

Objective Relation extraction (RE) is a fundamental task of natural language processing, which always draws plenty of attention from researchers, especially RE at the document-level. We aim to explore an effective novel method for document-level medical relation extraction. Methods We propose a novel edge-oriented graph neural network based on document structure and external knowledge for document-level medical RE, called SKEoG. This network has the ability to take full advantage of document structure and external knowledge. Results We evaluate SKEoG on two public datasets, that is, Chemical-Disease Relation (CDR) dataset and Chemical Reactions dataset (CHR) dataset, by comparing it with other state-of-the-art methods. SKEoG achieves the highest F1-score of 70.7 on the CDR dataset and F1-score of 91.4 on the CHR dataset. Conclusion The proposed SKEoG method achieves new state-of-the-art performance. Both document structure and external knowledge can bring performance improvement in the EoG framework. Selecting proper methods for knowledge node representation is also very important.

关键词： Medical relation extraction Graph neural network document structure External knowledge

来源：评论

学校读者我要写书评

暂无评论

Formalising document structure and Automatically Recognising document Elements: A Case Study on Automobile Repair Manuals 21st

Formalising Document Structure and Automatically Recognising...

引用

21st International Conference on Asia-Pacific Digital Libraries (ICADL)

作者： Sugino, Hodai Miyata, Rei Sato, Satoshi Nagoya Univ Nagoya Aichi Japan

ISBN: (纸本)9783030340582;9783030340575

Correct understanding of document structures is vital to enhancing various practices and applications, such as authoring and information retrieval. In this paper, with a focus on procedural documents of automobile repair manuals, we report a formalisation of document structure and an experiment to automatically classify sentences according to document structure. To formalise document structure, we first investigated what types of content are included in the target documents. Through manual annotation, we identified 26 indicative content categories (content elements). We then employed an existing standard for technical documents-the Darwin Information Typing Architecture-and formalised a detailed document structure for automobile repair tasks that specifies the arrangement of the content elements. We also examined the feasibility of automatic content element recognition in given documents by implementing sentence classifiers using multiple machine learning methods. The evaluation results revealed that support vector machine-based classifiers generally demonstrated high performance for in-domain data, while convolutional neural network-based classifiers are advantageous for out-of-domain data. We also conducted in-depth analyses to identify classification difficulties.

关键词： document structure Genre analysis Manual annotation Automatic text classification

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Sentence Embedding Using document structure-Based Context

Unsupervised Sentence Embedding Using Document Structure-Bas...

引用

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Lee, Taesung Park, Youngja IBM TJ Watson Res Ctr Yorktown Hts NY 10598 USA

ISBN: (纸本)9783030461478;9783030461461

We present a new unsupervised method for learning general-purpose sentence embeddings. Unlike existing methods which rely on local contexts, such as words inside the sentence or immediately neighboring sentences, our method selects, for each target sentence, influential sentences from the entire document based on the document structure. We identify a dependency structure of sentences using metadata and text styles. Additionally, we propose an out-of-vocabulary word handling technique for the neural network outputs to model many domain-specific terms which were mostly discarded by existing sentence embedding training methods. We empirically show that the model relies on the proposed dependencies more than the sequential dependency in many cases. We also validate our model on several NLP tasks showing 23% F1-score improvement in coreference resolution in a technical domain and 5% accuracy increase in paraphrase detection compared to baselines.

关键词： Sentence embedding document structure Out-of-vocabulary

来源：评论

学校读者我要写书评

暂无评论

Detecting document structure in a Very Large Corpus of UK Financial Reports 9

Detecting Document Structure in a Very Large Corpus of UK Fi...

引用

9th International Conference on Language Resources and Evaluation (LREC)

作者： El-Haj, Mahmoud Rayson, Paul Young, Steven Walker, Martin Univ Lancaster Sch Comp & Commun Lancaster LA1 4YW England Univ Lancaster Lancaster Univ Management Sch Lancaster LA1 4YW England Univ Manchester Manchester Business Sch Manchester M13 9PL Lancs England

ISBN: (纸本)9782951740884

In this paper we present the evaluation of our automatic methods for detecting and extracting document structure in annual financial reports. The work presented is part of the Corporate Financial Information Environment (CFIE) project in which we are using Natural Language Processing (NLP) techniques to study the causes and consequences of corporate disclosure and financial reporting outcomes. We aim to uncover the determinants of financial reporting quality and the factors that influence the quality of information disclosed to investors beyond the financial statements. The CFIE consists of the supply of information by firms to investors, and the mediating influences of information intermediaries on the timing, relevance and reliability of information available to investors. It is important to compare and contrast specific elements or sections of each annual financial report across our entire corpus rather than working at the full document level. We show that the values of some metrics e.g. readability will vary across sections, thus improving on previous research research based on full texts.

关键词： document structure annual reports readability

来源：评论

学校读者我要写书评

暂无评论

Fourier domain scoring with document structure consideration 4

Fourier domain scoring with document structure consideration

引用

4th International Conference on Active Media Technology

作者： Dusinski, Daniel Szczepaniak, Piotr S. Tech Univ Lodz Inst Comp Sci PL-90924 Lodz Poland

ISBN: (纸本)9781586036157

Recently, Fourier and cosine discrete transformations have been proposed for textual document retrieval and ranking. The advantage of those methods is that they use spatial information about flow of terms through documents. Here, we investigate the question if consideration of important document elements like titles, sections, sentences, etc. improves efficiency the original Fourier domain scoring method.

关键词： information retrieval discrete transform spatial information document structure word signal

来源：评论

学校读者我要写书评

暂无评论

A 3D audio only interactive web browser:: Using spatialization to convey hypermedia document structure 99

A 3D audio only interactive web browser:: Using spatializati...

引用

7th ACM International Multimedia Conference

作者： Goose, S Möller, C Siemens Corp Res Multimedia Dept Princeton NJ 08540 USA

ISBN: (纸本)0201485621

Interactive audio browsers provide both sighted and visually impaired users with access to the WWW. In addition to the desktop PC, audio browsing technology can be deployed that enable users to browse the WWW using a telephone or while driving a car. This paper describes a new conceptual model of the HTML document structure and its mapping to a 3D audio space. Novel features are discussed that provide information such as: an audio structural survey of the HTML document;accurate positional audio feedback of the source and destination anchors when traversing both inter-and intra-document links;a linguistic progress indicator;the announcement of destination document meta-information as new links are encountered. These new features can improve both the user's comprehension of the HTML document structure and their orientation within it. These factors, in turn, can improve the effectiveness of the browsing experience.

关键词： 3D audio spatialization document structure Hypertext WWW browsing

来源：评论

学校读者我要写书评

暂无评论

Estimating Legal document structure by Considering Style Information and Table of Contents 1

引用

Japanese-Society-of-Artificial-Intelligence International Symposium on Artificial Intelligence (JSAI-isAI)

作者： Hatsutori, Yoichi Yoshikawa, Katsumasa Imai, Haruki IBM Japan Ltd IBM Res Chuo Ku 19-21 Nihonbashi Hakozaki Cho Tokyo 1038510 Japan

ISBN: (数字)9783319615721

ISBN: (纸本)9783319615721;9783319615714

Text analytics is used to analyze diverse documents. For example, legal documents (such as contracts, ordinances, regulations, and global standards) must be analyzed for corporations to manage their business risk and meet compliance requirements. However, since documents are often stored or published as documents without a common structure, they need to be preprocessed to analyze them in subsequent text analytics. In particular, the following two forms of preprocessing are useful for text analytics: (1) extracting text, and (2) estimating document structure (such as chapters, sections, and subsections), which is used to define the range of topics or articles in a document. This paper presents a preprocessing method to estimate document structure from documents without a common structure. The proposed method follows rule-based approach, and consists of three algorithms: (1) one is based on style information, such as bold font;(2) another is based on numbered objects, such as sections;and (3) the other is based on a document's Table of Contents, which summarizes the document's structure. The accuracy of the proposed method is also evaluated by using 102 documents. The proposed method was found to be able to estimate document structure with 96.6% accuracy.

关键词： document structure Article extraction Article comparison Text analytics Law articles

来源：评论

学校读者我要写书评

暂无评论

Detecting and using document structure in scientific text 12

Detecting and using document structure in scientific text

引用

Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium

作者： Anita de Waard Sophia Ananiadou Maryann Martone Ágnes Sándor Hagit Shatkay Elsevier Labs Burlington VT USA University of Manchester Manchester United Kingdom University of California at San Diego San Diego CA USA Xerox Europe Grenoble France University of Delaware Newark DE USA

ISBN: (纸本)9781450307819

The detection of discourse structure of scientific documents is important for a number of tasks, including biocuration efforts, text summarisation, and the creation of improved formats for scientific publishing. Currently, many parallel efforts exist to detect a range of discourse elements at different levels of granularity, and for different purposes, including extraction of information from complex documents, alignment of parallel corpora across languages, and support for document summarization (particularly multi-document summarization). Another interesting class of applications comes from "bibliometrics" and "scientometrics". For example, for analysis of argument structure in full text articles from the scientific literature, it may be important to know where a particular reference is cited or where a particular statement is made (Background, Discussion, etc.). Another application might include tracking over time where (in what sections) an entity or concept is mentioned, to determine whether the mentions migrate from research claims into the "Background" or eventually to the "Methods" sections of articles, as the concept moves from "foreground" (subject of the research) to "background". In this panel we would like to, explore compare, contrast and evaluate different scientific discourse annotation schemes and tools, in order to answer questions such as: What motivates a certain level, method, viewpoint for annotating scientific text?What is the annotation level for a unit of argumentation: an event, a sentence, a segment? What are advantages and disadvantages of all three?How easily can different schemes to be applied to texts? Are they easily trainable?Which schemes are most portable? Can they be applied to both full papers and abstracts? Can they be applied to texts in different domains?How granular should annotation schemes be? What are the advantages/disadvantages of fine and coarse grained annotation categories?What correlations occur among document struct

关键词： natural language processing document structure scientific discourse annotation

来源：评论

学校读者我要写书评

暂无评论

document Sub-structure in Neural Machine Translation 12

Document Sub-structure in Neural Machine Translation

引用

12th International Conference on Language Resources and Evaluation (LREC)

作者： Dobreva, Radina Zhou, Jie Bawden, Rachel Univ Edinburgh Sch Informat 10 Crichton St Edinburgh Midlothian Scotland Alibaba Grp 969 West Wen Yi Rd Hangzhou Peoples R China

ISBN: (纸本)9791095546344

Current approaches to machine translation (MT) either translate sentences in isolation, disregarding the context they appear in, or model context at the level of the full document, without a notion of any internal structure the document may have. In this work we consider the fact that documents are rarely homogeneous blocks of text, but rather consist of parts covering different topics. Some documents, such as biographies and encyclopedia entries, have highly predictable, regular structures in which sections are characterised by different topics. We draw inspiration from Louis and Webber (2014) who use this information to improve statistical MT and transfer their proposal into the framework of neural MT. We compare two different methods of including information about the topic of the section within which each sentence is found: one using side constraints and the other using a cache-based model. We create and release the data on which we run our experiments - parallel corpora for three language pairs (Chinese-English, French-English, Bulgarian-English) from Wikipedia biographies, which we extract automatically, preserving the boundaries of sections within the articles.

关键词： machine translation document structure corpus creation context Wikipedia parallel corpus

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：