Comparison and Classification of Documents Based on Layout Similarity

This paper describes features and methods for document image comparison and classification at the spatial layout level. The methods are useful for visual similarity based document retrieval as well as fast algorithms for initial document type classification without OCR. A novel feature set called interval encoding is introduced to capture elements of spatial layout. This feature set encodes region layout information in fixed-length vectors by capturing structural characteristics of the image. These fixed-length vectors are then compared to each other through a Manhattan distance computation for fast page layout comparison. The paper describes experiments and results to rank-order a set of document pages in terms of their layout similarity to a test document. We also demonstrate the usefulness of the features derived from interval coding in a hidden Markov model based page layout classification system that is trainable and extendible. The methods described in the paper can be used in various document retrieval tasks including visual similarity based retrieval, categorization and information extraction.     

高校图书馆图书采购招标的再思考

近年来,图书采购招标成为图书采购的主要方式,它改变了传统的采访模式,对采访工作提出了新的要求。文章结合实际,论述了采购招标形势下采访工作的新变化、新要求,以及采访人员应采取的相应对策。     

基于中文信息处理的古籍整理研究评述

随着计算机技术的飞速发展,基于中文信息处理的古籍整理已成为近年来的研究热点,并且取得一些可喜的成绩。在搜集整理当前研究与应用成果的基础上,从古籍的自动录入、自动断句、自动编纂以及自动翻译等方面对基于中文信息处理技术的古籍整理的研究现状进行概述,同时分别探讨这几个方面仍然存在的问题,并展望其今后的研究工作。      

入藏馆量与学术著作影响力评价

[目的/意义]探索入藏馆量在学术著作评价工作中的应用，为学术评价提供参考。[方法/过程]从指标数据的产生机制、获取及应用情况3个方面讨论入藏馆量在学术著作影响力评价中的适用性，并以WorldCat为例进行实证分析与讨论。[结果/结论]入藏馆量数据通常来源于国家或国际图书馆联盟目录，在获取数据时，应根据选择的指标来源选择合适的检索方式，以准确获取著作的入藏馆量信息。在应用入藏馆量时，应考虑入藏图书馆的类型、地域等属性才能更加全面、准确评价著作的影响力。     

Adding Objectivity to Standard Setting: Evaluating Consequence Using the Conscious and Subconscious Weight Methods

Standard setting is arguably one of the most subjective techniques in test development and psychometrics. The decisions when scores are compared to standards, however, are arguably the most consequential outcomes of testing. Providing licensure to practice in a profession has high stake consequences for the public. Denying graduation or forcing remediation has high-impact consequences for students. Unfortunately, tests that classify individuals are subjected to false positive and false negative misclassifications. When determining a standard, standard setting panelists implicitly consider the negative consequences of the decisions made from test use. We propose the conscious weight method and subconscious weight method to bring more objectivity to the standard setting process. To do this, these methods quantify the relative harm of the negative consequences of false positive and false negative misclassification.     

The impact of deep learning on document classification using semantically rich representations

This paper presents a semantically rich document representation model for automatically classifying financial documents into predefined categories utilizing deep learning. The model architecture consists of two main modules including document representation and document classification. In the first module, a document is enriched with semantics using background knowledge provided by an ontology and through the acquisition of its relevant terminology. Acquisition of terminology integrated to the ontology extends the capabilities of semantically rich document representations with an in depth-coverage of concepts, thereby capturing the whole conceptualization involved in documents. Semantically rich representations obtained from the first module will serve as input to the document classification module which aims at finding the most appropriate category for that document through deep learning. Three different deep learning networks each belonging to a different category of machine learning techniques for ontological document classification using a real-life ontology are used.Multiple simulations are carried out with various deep neural networks configurations, and our findings reveal that a three hidden layer feedforward network with 1024 neurons obtain the highest document classification performance on the INFUSE dataset. The performance in terms of F1 score is further increased by almost five percentage points to 78.10% for the same network configuration when the relevant terminology integrated to the ontology is applied to enrich document representation. Furthermore, we conducted a comparative performance evaluation using various state-of-the-art document representation approaches and classification techniques including shallow and conventional machine learning classifiers.     

面向先秦典籍的知识本体构建技术研究

[目的/意义] 构建面向典籍文本的语义本体，能够促进典籍文本的挖掘与分析。然而由于典籍文本与现代文本在语法上存在较大差异，给面向典籍的语义本体构建带来了困难。[方法/过程] 本文运用自然语言处理技术探讨针对先秦典籍的本体构建方法。以国际上文化遗产领域通用的CIDOC CRM为框架，设计先秦典籍本体模型。针对典籍文本内容的特点及句法特征，将规则抽取与条件随机场方法相结合，提出一套本体实例自动获取技术，并以《左传》为实验语料进行测试。[结果/结论] 实验表明，本文所提出的本体实例抽取技术能够较好地提高面向典籍文本的本体构建效率。基于规则的本体实例抽取实验F值在93%左右，基于条件随机场的本体实例抽取最佳特征模板的F值为82.51%。在本体实例获取中，词性信息和位置信息具有重要作用。     

A joint learning approach with knowledge injection for zero-shot cross-lingual hate speech detection

Hate speech is an increasingly important societal issue in the era of digital communication. Hateful expressions often make use of figurative language and, although they represent, in some sense, the dark side of language, they are also often prime examples of creative use of language. While hate speech is a global phenomenon, current studies on automatic hate speech detection are typically framed in a monolingual setting. In this work, we explore hate speech detection in low-resource languages by transferring knowledge from a resource-rich language, English, in a zero-shot learning fashion. We experiment with traditional and recent neural architectures, and propose two joint-learning models, using different multilingual language representations to transfer knowledge between pairs of languages. We also evaluate the impact of additional knowledge in our experiment, by incorporating information from a multilingual lexicon of abusive words. The results show that our joint-learning models achieve the best performance on most languages. However, a simple approach that uses machine translation and a pre-trained English language model achieves a robust performance. In contrast, Multilingual BERT fails to obtain a good performance in cross-lingual hate speech detection. We also experimentally found that the external knowledge from a multilingual abusive lexicon is able to improve the models’ performance, specifically in detecting the positive class. The results of our experimental evaluation highlight a number of challenges and issues in this particular task. One of the main challenges is related to the issue of current benchmarks for hate speech detection, in particular how bias related to the topical focus in the datasets influences the classification performance. The insufficient ability of current multilingual language models to transfer knowledge between languages in the specific hate speech detection task also remain an open problem. However, our experimental evaluation and our qualitative analysis show how the explicit integration of linguistic knowledge from a structured abusive language lexicon helps to alleviate this issue.     

Millennials’ Reading Behavior in the Digital Age: A Case Study of Pakistani University Students

Abstract

This article uncovers the reading trends of Millennials living in Pakistan by investigating their reading behavior within the digital paradigm. A cross-sectional survey-based quantitative research design was adopted. Masters students (16?years education) from the Higher Education Commission (HEC) recognized universities of Lahore, Pakistan was the study population. A total of 515 masters’ level students from 7 universities participated in the survey. The participants were recruited by employing a two-stage stratified purposive total population sampling technique. The study findings confirmed that despite their preferences for print material, Millennials were using electronic material for reading more frequently. However, the study showed that the reading purpose influences the choice of the reading format. Furthermore, the availability of electronic reading content in the public domain and open access contents may be a reason for increased use of e-content, as free websites were the preferred method of millennials for obtaining reading material. Social networking websites and intelligent search engines like “Google” were also in use and play a role in finding the relevant information and reading e-content. The study shows that the digital environment has a significant impact on the reading behavior of individuals, a fact which needs to be considered by academics, practitioners, and the individuals themselves. It is considered a baseline study that opens various potential directions and avenues for future research.