MBNER:面向生物医学领域的多种实体识别系统

生物命名实体识别,就是从生物医学文本中识别出指定类型的名称。目前,面向生物医学领域的实体识别研究不断出现,从海量生物医学文本自动提取生物实体信息的技术变得尤为重要。该文介绍了一个面向生物医学领域的多实体识别系统MBNER(Multiple Biomedical Named Entity Recognizer)。该系统可以在生物医学文本中同时识别出基因(蛋白质)、药物、疾病实体,其对基因(蛋白质)、药物、疾病实体识别在各自数据集上分别得到了89.05%,76.73%,90.12%的综合分类率(F-score)。该系统以可视化的形式给出对三种命名实体的识别结果。     

条件随机域与上下文线索结合的生物实体识别

介绍一个用于在生物医学文献中识别基因、蛋白质等生物实体的识别方法。该方法基于条件随机域方法,选取适当特征进行实体识别,利用上下文线索进一步提高识别性能。实验结果表明上下文线索的引入使识别性能在条件随机域方法基础上提高了近3%,从而获得了较好的最终识别效果。     

几种基于机器学习的生物命名实体识别模型比较

已有的大量生物医学文本为人们提供了充足的资料,但却没有足够好的工具来帮助人们从中获取信息和知识。而命名实体识别则在信息检索、信息抽取及知识发现等这样的应用中起着很重要的作用。本文基于JNLPBA生物命名实体识别任务,简要介绍了目前几种在生物医学文本中常用的基于机器学习的命名实体识别模型,并进行比较及常规讨论,同时也提供了一些相关的背景信息。     

几种基于机器学习的生物命名实体识别模型比较

已有的大量生物医学文本为人们提供了充足的资料，但却没有足够好的工具来帮助人们从中获取信息和知识。而命名实体识别则在信息检索、信息抽取及知识发现等这样的应用中起着很重要的作用。本文基于JNLPBA生物命名实体识别任务，简要介绍了目前几种在生物医学文本中常用的基于机器学习的命名实体识别模型，并进行比较及常规讨论，同时也提供了一些相关的背景信息。     

基于深度学习的命名实体识别综述

命名实体识别是自然语言处理的基础任务之一,目的是从非结构化的文本中识别出所需的实体及类型,其识别的结果可用于实体关系抽取、知识图谱构建等众多实际应用。近些年,随着深度学习在自然语言处理领域的广泛应用,各种基于深度学习的命名实体识别方法均取得了较好的效果,其性能全面超越传统的基于人工特征的方法。该文从三个方面介绍近期基于深度学习的命名实体识别方法: 第一,从输入层、编码层和解码层出发,介绍命名实体识别的一般框架;第二,分析汉语命名实体识别的特点,着重介绍各种融合字词信息的模型;第三,介绍低资源的命名实体识别,主要包括跨语言迁移方法、跨领域迁移方法、跨任务迁移方法和集成自动标注语料的方法等。最后,总结相关工作,并提出未来可能的研究方向。     

生物医学文本挖掘技术的研究与进展

生物医学研究是二十一世纪最受关注的研究领域之一,该领域发表了巨量的研究论文,已经达到年平均60万篇以上。如何在规模巨大的研究文献中有效地获取相关知识,是该领域研究者所面临的挑战。作为生物信息学分支之一的生物医学文本挖掘技术就是一项高效自动地获取相关知识的新探索,近年来取得了较大进展。这篇综述介绍了生物医学文本挖掘的主要研究方法和成果,即基于机器学习方法的生物医学命名实体识别、缩写词和同义词的识别、命名实体关系抽取,以及相关资源建设、相关评测会议和学术会议等。此外还简要介绍了国内研究现状,最后对该领域近期发展作了展望。     

一种统计和词性相结合的命名实体发现方法

在利用专业文献自动构建知识库的过程中， 需要正确识别专业文献中的命名实体。文章针对命名实体识别问题．提出了一种以统计为主发现命名实体的方法。该方法利用切分标记将原文切分为较短的汉字串，采用自增长统计算法从汉字串中生成原始模式集，并利用统计信息和词性信息筛选出命名实体。     

基于生物医学文献的蛋白质关系发现

实验提出了一种基于词频统计的蛋白质关系知识发现方法,该方法首先通过生物命名实体识别技术识别出蛋白质实体,然后统计共出现频率,形成候选实体对,从而发现最有可能的实体关联。     

基于深度学习的命名实体识别研究综述

命名实体识别技术是信息抽取、机器翻译、问答系统等多种自然语言处理技术中一项重要的基本任务。近年来,基于深度学习的命名实体识别技术成为一大研究热点。为了方便研究者们了解基于深度学习的命名实体识别研究进展及未来发展趋势,对当前基于卷积神经网络、循环神经网络、transformer模型以及其他一些命名实体识别方法展开综述性介绍,对四类方法进行了深入分析和对比。同时对命名实体识别应用领域以及所涉及到的数据集和评测方法进行了介绍,并对未来的研究方向进行了展望。     

基于生物医学文献的蛋白质关系发现

实验提出了一种基于词频统计的蛋白质关系知识发现方法,该方法首先通过生物命名实体识别技术识别出蛋白质实体,然后统计共出现频率,形成候选实体对,从而发现最有可能的实体关联。     

A multi-strategy approach to biological named entity recognition

Recognizing and disambiguating bio-entities (genes, proteins, cells, etc.) names are very challenging tasks as some biologica databases can be outdated, names may not be normalized, abbreviations are used, syntactic and word order is modified, etc. Thus, the same bio-entity might be written into different ways making searching tasks a key obstacle as many candidate relevant literature containing those entities might not be found. As consequence, the same protein mention but using different names should be looked for or the same discovered protein name is being used to name a new protein using completely different features hence named-entity recognition methods are required. In this paper, we developed a bio-entity recognition model which combines different classification methods and incorporates simple pre-processing tasks for bio-entities (genes and proteins) recognition is presented. Linguistic pre-processing and feature representation for training and testing is observed to positively affect the overall performance of the method, showing promising results. Unlike some state-of-the-art methods, the approach does not require additional knowledge bases or specific-purpose tasks for post processing which make it more appealing. Experiments showing the promise of the model compared to other state-of-the-art methods are discussed.     

Recent trends in knowledge and data integration for the life sciences

Abstract: The bioscience field has seen some spectacular advances in genomic and proteomic technologies that are able to deliver vast quantities of information on cellular activity. Such technologies are of critical importance to biology, medical science and in drug discovery. However, living systems are highly complex and to fully exploit these technologies requires knowledge at many different levels. Information such as genome sequence data, gene expression data, protein-to-protein interactions and metabolic pathways is required to understand the complexity of biological processes. The challenge for bioinformatics is to tackle the problem of fragmentation of knowledge by integrating the many sources of heterogeneous information into a coherent entity. Another problem is that the high level of biological complexity and the fragmented nature of biological research has meant that it is difficult to keep fully conversant with the latest research and discoveries. Progress in one area of biology may have implications for other areas but the dissemination of this knowledge is not straightforward; difficulties such as differences in naming conventions for genes and biological processes has led to confusion and the lack of productivity. This paper reviews the most recent research to overcome the fragmentation problem where technologies such as text mining and ontologies are used within the knowledge discovery process and the specific technical challenges they address.     

基于膨胀卷积迭代与注意力机制的实体名识别方法

针对传统实体名识别方法无法兼顾文本序列提取特征的有效性和神经网络模型训练速度的问题,提出一种基于迭代膨胀卷积神经网络(IDCNN)与注意力机制(ATT)的实体名识别方法。IDCNN可利用GPU并行计算的优化能力,保留长短期记忆神经网络的特性,即用简单的结构记录尽可能多的输入信息,并在准确提取文本序列特征的同时加快神经网络模型的训练速度。通过引入ATT运用文本语法信息和单词词性信息,从众多文本特征中选择对实体名识别更关键的特征,从而提高文本特征提取的准确性。在新闻数据集和微博数据集上的实验结果表明,神经网络模型的训练速度比传统的双向长短期记忆神经网络有显著提升,基于注意力的实体名识别方法的评价指标比传统的无注意力机制方法提高2%左右。     

基于改进的PSO算法的关键蛋白质识别方法研究

关键蛋白质是生物体内维持所有生命活动最重要的物质基础。随着高通量技术的发展,如何从蛋白质相互作用网络中识别出关键蛋白质成为目前蛋白质组学的研究热点。针对大部分现有方法仅仅基于网络拓扑结构信息进行识别以及蛋白质相互作用数据假阳性高的问题,提出了改进的粒子群算法来识别关键蛋白质。通过综合考虑网络拓扑结构特性和多源生物属性信息构建了高质量的加权网络,还考虑使用蛋白质节点间联系的紧密程度来衡量蛋白质的关键性,并扩展局部网络拓扑至二阶邻居,大大提高了预测的准确率。提出了衡量top-p关键蛋白质的整体性指标,降低了计算复杂度。在标准数据集上的实验结果表明,与其他经典算法相比,所提算法更具优势,能够识别出更多的蛋白质,具有较高的准确率。     

基于域名系统知识图谱的CDN域名识别技术

内容分发网络（content delivery network,CDN）是互联网上的重要基础设施,目前识别CDN域名的方法主要利用域名字符特征、HTTP关键字和DNS记录等,识别范围有限。针对大规模识别CDN域名的问题,提出了基于域名系统知识图谱的CDN域名识别技术。根据域名系统的特征进行本体建模、数据获取、知识图谱构建,通过分析域名系统相关数据获取CDN服务特征。将CDN域名作为知识图谱域名节点的属性,定义推理规则,通过知识图谱内包含的实体、关系和属性进行关联分析,识别CDN域名。基于该方法对Alexa排名前100万域名及其部分子域名进行建模识别,构建了超百万节点和关系的域名系统知识图谱。实验结果表明,该方法在不通过手工识别构建样本集的情况下可以达到88%的分类精度和86%的F1指数。     

Grammatical inference in bioinformatics

Bioinformatics is an active research area aimed at developing intelligent systems for analyses of molecular biology. Many methods based on formal language theory, statistical theory, and learning theory have been developed for modeling and analyzing biological sequences such as DNA, RNA, and proteins. Especially, grammatical inference methods are expected to find some grammatical structures hidden in biological sequences. In this article, we give an overview of a series of our grammatical approaches to biological sequence analyses and related researches and focus on learning stochastic grammars from biological sequences and predicting their functions based on learned stochastic grammars.     

基于增强BiLSTM-CRF模型的推文恶意软件名称识别

针对推文中恶意软件名称识别任务存在的文本简短、非正式、实体类别单一以及实体歧义等问题,提出了一种基于BERT-BiLSTM-Self-attention-CRF的实体识别方法,以实现推文中恶意软件名称的自动识别。在BiLSTM-CRF模型的基础上,利用BERT模型编码单词语境信息,提升词嵌入的上下文语义质量,增强原有模型的语义消歧能力;同时,借助Self-attention机制学习单词间关系和句子结构特征,利用加权表征帮助单一类别实体的解码,以提升恶意软件名称实体的识别效果。通过构建包含恶意软件名称实体的推文标记数据集进行实验测试,结果表明,提出的方法可以实现更好的性能,其精确率、召回率、F1值分别为86.38%,84.73%,85.55%,相较于基线模型BiLSTM-CRF,F1值提升了12.61%。     

Textual data compression in computational biology: Algorithmic techniques

In a recent review [R. Giancarlo, D. Scaturro, F. Utro, Textual data compression in computational biology: a synopsis, Bioinformatics 25 (2009) 1575–1586] the first systematic organization and presentation of the impact of textual data compression for the analysis of biological data has been given. Its main focus was on a systematic presentation of the key areas of bioinformatics and computational biology where compression has been used together with a technical presentation of how well-known notions from information theory have been adapted to successfully work on biological data. Rather surprisingly, the use of data compression is pervasive in computational biology. Starting from that one, the focus of this companion review is on the computational methods involved in the use of data compression in computational biology. Indeed, although one would expect ad hoc adaptation of compression techniques to work on biological data, unifying and homogeneous algorithmic approaches are emerging. Moreover, given that experiments based on parallel sequencing are the future for biological research, data compression techniques are among a handful of candidates that seem able, successfully, to deal with the deluge of sequence data they produce; although, until now, only in terms of storage and indexing, with the analysis still being a challenge. Therefore, the two reviews, complementing each other, are perceived to be a useful starting point for computer scientists to get acquainted with many of the computational challenges coming from computational biology in which core ideas of the information sciences are already having a substantial impact.