RoBGP:A Chinese Nested Biomedical Named Entity Recognition Model Based on RoBERTa and Global Pointer

Named Entity Recognition(NER)stands as a fundamental task within the field of biomedical text mining,aiming to extract specific types of entities such as genes,proteins,and diseases from complex biomedical texts and categorize them into predefined entity types.This process can provide basic support for the automatic construction of knowledge bases.In contrast to general texts,biomedical texts frequently contain numerous nested entities and local dependencies among these entities,presenting significant challenges to prevailing NER models.To address these issues,we propose a novel Chinese nested biomedical NER model based on RoBERTa and Global Pointer(RoBGP).Our model initially utilizes the RoBERTa-wwm-ext-large pretrained language model to dynamically generate word-level initial vectors.It then incorporates a Bidirectional Long Short-Term Memory network for capturing bidirectional semantic information,effectively addressing the issue of long-distance dependencies.Furthermore,the Global Pointer model is employed to comprehensively recognize all nested entities in the text.We conduct extensive experiments on the Chinese medical dataset CMeEE and the results demonstrate the superior performance of RoBGP over several baseline models.This research confirms the effectiveness of RoBGP in Chinese biomedical NER,providing reliable technical support for biomedical information extraction and knowledge base construction.

SHEL:a semantically enhanced hardware-friendly entity linking method

With the help of pre-trained language models,the accuracy of the entity linking task has made great strides in recent years.However,most models with excellent performance require fine-tuning on a large amount of training data using large pre-trained language models,which is a hardware threshold to accomplish this task.Some researchers have achieved competitive results with less training data through ingenious methods,such as utilizing information provided by the named entity recognition model.This paper presents a novel semantic-enhancement-based entity linking approach,named semantically enhanced hardware-friendly entity linking(SHEL),which is designed to be hardware friendly and efficient while maintaining good performance.Specifically,SHEL's semantic enhancement approach consists of three aspects:(1)semantic compression of entity descriptions using a text summarization model;(2)maximizing the capture of mention contexts using asymmetric heuristics;(3)calculating a fixed size mention representation through pooling operations.These series of semantic enhancement methods effectively improve the model's ability to capture semantic information while taking into account the hardware constraints,and significantly improve the model's convergence speed by more than 50%compared with the strong baseline model proposed in this paper.In terms of performance,SHEL is comparable to the previous method,with superior performance on six well-established datasets,even though SHEL is trained using a smaller pre-trained language model as the encoder.

Tracking topological entity changes in 3D collaborative modeling systems

One of the key problems in collaborative geometric modeling systems is topological entity correspondence when topolog- ical structure of geometry models on collaborative sites changes, ha this article, we propose a solution for tracking topological entity alterations in 3D collaborative modeling environment. We firstly make a thorough analysis and detailed categorization on the altera- tion properties and causations for each type of topological entity, namely topological face and topological edge. Based on collabora- tive topological entity naming mechanism, a data structure called TEST （Topological Entity Structure Tree） is introduced to track the changing history and current state of each topological entity, to embody the relationship among topological entities. Rules and algo- rithms are presented for identification of topological entities referenced by operations for correct execution and model consistency. The algorithm has been verified within the prototype we have implemented with ACIS.

Chinese Named Entity Recognition with Character-Level BLSTM and Soft Attention Model

Unlike named entity recognition(NER)for English,the absence of word boundaries reduces the final accuracy for Chinese NER.To avoid accumulated error introduced by word segmentation,a deep model extracting character-level features is carefully built and becomes a basis for a new Chinese NER method,which is proposed in this paper.This method converts the raw text to a character vector sequence,extracts global text features with a bidirectional long short-term memory and extracts local text features with a soft attention model.A linear chain conditional random field is also used to label all the characters with the help of the global and local text features.Experiments based on the Microsoft Research Asia(MSRA)dataset are designed and implemented.Results show that the proposed method has good performance compared to other methods,which proves that the global and local text features extracted have a positive influence on Chinese NER.For more variety in the test domains,a resume dataset from Sina Finance is also used to prove the effectiveness of the proposed method.

Entity generation algorithm based on reference expansion

The extraction and understanding of text knowledge become increasingly crucial in the age of big data.One of the current research areas in the field of natural language processing(NLP)is how to accurately understand the text and collect accurate linguistic information because Chinese vocabulary is diverse and ambiguous.This paper mainly studies the candidate entity generation module of the entity link system.The candidate entity generation module constructs an entity reference expansion algorithm to improve the recall rate of candidate entities.In order to improve the efficiency of the connection algorithm of the entire system while ensuring the recall rate of candidate entities,we design a graph model filtering algorithm that fuses shallow semantic information to filter the list of candidate entities,and verify and analyze the efficiency of the algorithm through experiments.By analyzing the related technology of the entity linking algorithm,we study the related technology of candidate entity generation and entity disambiguation,improve the traditional entity linking algorithm,and give an innovative and practical entity linking model.The recall rate exceeds 82%,and the link accuracy rate exceeds 73%.Efficient and accurate entity linking can help machines to better understand text semantics,further promoting the development of NLP and improving the users’knowledge acquisition experience on the text.

Coding of Topological Entities in Feature-Based Parametric Modeling System

How to identify topological entities during rebuilding features is a critical problem in Feature-Based Parametric Modeling System (FBPMS). In the article, authors proposes a new coding approach to distinguish different entities. The coding mechanism is expatiated,and some typical examples are presented. At last, the algorithm of decoding is put forward based on set theory.

汽车故障知识图谱构建及应用研究

知识图谱技术对汽车高效的故障诊断具有重要的意义,现有汽车故障知识图谱构建存在着实体识别模型效果不佳、无法解决嵌套实体等问题。针对上述问题,通过采用全词掩码的预训练语义模型、加入对抗训练和改进嵌套实体识别模型的方式提高实体识别模型效果,提出了一种改进的嵌套实体识别模型。实验结果表明,所提模型F1值(F_(1))、精确率(P)和召回率(R)相比基线模型分别提高了3.56%、4.08%、3.05%,相比其他模型也有不同程度的提高,验证了所提模型对汽车维修领域实体识别具有显著效果。同时,基于构建的汽车故障知识图谱,实现了汽车故障知识智能问答原型系统,展示了知识图谱技术在汽车故障诊断与维护领域的应用前景。

基于连续提示注入与指针网络的农业病害命名实体识别

针对农业病害领域命名实体识别过程中存在的预训练语言模型利用不充分、外部知识注入利用率低、嵌套命名实体识别率低的问题,本文提出基于连续提示注入和指针网络的命名实体识别模型CP-MRC(Continuous prompts for machine reading comprehension)。该模型引入BERT(Bidirectional encoder representation from transformers)预训练模型,通过冻结BERT模型原有参数,保留其在预训练阶段获取到的文本表征能力;为了增强模型对领域数据的适用性,在每层Transformer中插入连续可训练提示向量;为提高嵌套命名实体识别的准确性,采用指针网络抽取实体序列。在自建农业病害数据集上开展了对比实验,该数据集包含2933条文本语料,8个实体类型,共10414个实体。实验结果显示,CP-MRC模型的精确率、召回率、F1值达到83.55%、81.4%、82.4%,优于其他模型;在病原、作物两类嵌套实体的识别率较其他模型F1值提升3个百分点和13个百分点,嵌套实体识别率明显提升。本文提出的模型仅采用少量可训练参数仍然具备良好识别性能,为较大规模预训练模型在信息抽取任务上的应用提供了思路。

基于知识图谱的建筑施工安全风险量化与分析

为了提高建筑施工安全风险管理的信息化水平,以建筑施工活动及事故风险类型为研究对象,建立施工安全知识图谱。通过知识图谱改进作业条件危险性评价法(LEC)实现安全风险的定量计算,并基于知识图谱进行风险位置识别和不安全因素分析。研究提出安全风险虚体实化理念,实现了安全风险信息在数字空间实体化表达;基于建筑信息模型(Building Information Modeling, BIM)和知识图谱技术,建立了建筑施工安全风险信息模型(Building Construction Safety Risk Information Model, BCSRIM)。该模型有效避免了传统LEC法中主观因素产生的影响,实现了建筑施工安全风险定量计算、风险位置识别、风险分析及可视化管理。利用Revit二次开发技术,在Microsoft Visual Studio中使用C#语言连接Neo4j图数据库,完成了基于知识图谱的BCSRIM的开发。试验显示,研究提出的BCSRIM对提高施工现场的管理水平具有较高的实用价值。

新型农业经营主体促进山区小农户机械化的“滴涓效应”研究——以云南山区为例

本文旨在研究促进山区小农户与现代农业衔接的路径和机理。通过对云南省山区小农户的调查数据,采用回归和调节模型进行实证分析,验证促进山区小农户机械化水平的外部和内部路径以及相关机理的有效性,并探讨新型农业主体对山区小农户机械化水平影响的“涓滴效应”。研究结果表明,山区小农户的机械化水平主要受其社会和自然资源的影响以及内部互助行为的作用。新型农业经营主体在提升山区小农户整体机械化水平方面并不显著,但在提升部分山区小农户的机械化水平方面具有显著作用。农业企业的带动效应对于提升“非合作社社员”和“未获得免费培训”的山区小农户机械化水平起到明显的促进作用。而农民合作社仅在提升合作社社员的机械化水平方面发挥显著作用。因此,建议加大山地农业机械的研发投入,增强新型农业经营主体在提升小农户整体现代农业水平方面的作用,以促进小农户与现代农业的有机衔接。

自适应特征融合的多模态实体对齐研究

多模态数据间交互式任务的兴起对于综合利用不同模态的知识提出了更高的要求,因此融合不同模态知识的多模态知识图谱应运而生.然而,现有多模态知识图谱存在图谱知识不完整的问题,严重阻碍对信息的有效利用.缓解此问题的有效方法是通过实体对齐进行知识图谱补全.当前多模态实体对齐方法以固定权重融合多种模态信息,在融合过程中忽略不同模态信息贡献的差异性.为解决上述问题,设计一套自适应特征融合机制,根据不同模态数据质量动态融合实体结构信息和视觉信息.此外,考虑到视觉信息质量不高、知识图谱之间的结构差异也影响实体对齐的效果,本文分别设计提升视觉信息有效利用率的视觉特征处理模块以及缓和结构差异性的三元组筛选模块.在多模态实体对齐任务上的实验结果表明,提出的多模态实体对齐方法的性能优于当前最好的方法.

基于RoBERTa-Span-Attack的标签指针网络军事命名实体识别

军事领域文本中存在大量军事实体信息,准确识别这些信息是军事文本信息提取和构建军事知识图谱的基础性任务。首先,提出了一种基于RoBERTa预训练模型、跨度和对抗训练的标签指针网络的融合深度模型(RoBERTa-Span-Attack),用于中文军事命名实体识别;然后,采用了一种基于Span的标签指针网络,同时完成实体的起止位置和类别的识别任务;最后,在模型训练过程中加入对抗训练策略,通过添加一些扰动来生成对抗样本进行训练。在军事领域数据集上的实验结果表明:所提出的军事领域命名实体识别模型相较于BERT-CRF、BERT-Softmax和BERT-Span,在识别准确度上具有更优的效果。

融合时序分类的科技领域实体增长预测研究

[目的/意义]科技领域实体增长机制是进行预测型科技情报分析的核心,要有效地进行科技发展态势感知和预测,必须深入了解科技领域细粒度知识增长机制。文章提出并验证了融合时序分类的科技领域实体增长预测方案。[方法/过程]首先,根据实体词频时间序列的增长模式,将实体分为可拟合、有趋势和无规律3种类别;其次,利用曲线拟合、局部加权回归方法抽取特征,构建特征向量,再用MLP模型实现了高精度的实体分类;最后,构建融合时序分类的集成模型与基线模型进行对比验证效果。[结果/结论]根据实验结果,验证显示集成预测模型相对于基线模型,误差减少了13%以上,进一步证实了预测结果在科学性和准确性方面的优势。综合考虑,所提出的融合时间序列分类的实体增长预测方案在可行性和应用价值方面具备潜力。

面向技术识别的专利实体抽取--以类脑智能领域为例

[研究目的]专利实体抽取是基于专利文本的技术识别的基础。目前专利实体抽取任务面临自动化程度和准确率较低等问题,该研究从两方面对此进行改进:一是建立特定领域的高质量专利语料库,二是将先进的算法模型运用到专利实体抽取中。[研究方法]定义了包含13种实体类型的细粒度信息体系,并据此对921篇类脑智能专利的标题和摘要进行人工标注,此后运用Bert-BiLSTM-CRF模型,融合深度学习和机器学习对类脑智能专利实体进行识别。[研究结论]模型在总体上获得0.8的准确率、召回率和F1值,不同类型实体的识别效果具有差异。为了验证模型的性能,设计了几个对比实验。结果显示,微调数据和增加训练规模可以提高模型性能,本模型性能优于同时期一些经典模型。

引入知识增强和对比学习的知识图谱补全

知识图谱补全是提高知识图谱质量的重要手段,主要分为基于结构和基于描述的方法。基于结构的补全方法对图谱中常见的长尾实体推理性能表现不佳,基于描述的补全方法在描述信息利用和负样本信息学习方面存在不足。针对上述问题,提出基于知识增强的知识图谱补全方法KEKGC。设计一种特定模板,将三元组及其描述信息通过人工定义的模板转换为连贯的自然语言描述语句输入预训练语言模型,增强语言模型对三元组结构知识与描述知识的理解能力。在此基础上,提出一种对比学习框架来提高链接预测任务的效率与准确率,通过建立记忆库存储实体嵌入向量,从中选择正负样本并结合Info NCE损失进行训练。实验结果显示,相较于MEM-KGC,KEKGC在WN18RR数据集上链接预测任务的平均倒数秩(MRR)提升了5.5,Hits@1、Hits@3、Hits@10指标分别提升了2.8、0.7、4.2个百分点,三元组分类任务准确率达到94.1%,表明所提方法具有更高的预测准确率与更好的泛化能力,尤其对于长尾实体,能够有效提升图谱补全的效果与效率。

基于边界感知的工业设备故障命名实体识别方法

命名实体识别在识别工业设备故障方面发挥关键作用,有助于故障预测、维护管理和智能决策。针对工业设备故障数据中存在的嵌套结构和长跨度问题,提出一种边界感知的实体识别方法。该方法通过边界感知精准定位实体跨距,并结合类别预测判断实体跨距的所属类别,以提高识别性能。此外,为解决标注数据的缺乏的问题,还构建面向工业设备故障的实体识别数据集。实验结果证明了该方法在工业设备故障实体识别方面的有效性,并为后续数据分析和知识图谱的构建提供了坚实基础。

室内实景三维重建技术综述

构建语义丰富、几何精确且拓扑完备的室内三维模型是实景三维中国建设中一项富有挑战性的任务,在室内导航与位置服务、虚拟现实、智能家居等领域都有重要的应用价值。室内空间结构布局复杂、实体要素类型多样及杂乱遮挡等因素给室内实景三维重建带来诸多挑战。近些年,室内实景三维重建受到广泛关注,然而关于现有方法的系统性总结仍较为欠缺。本文对室内实景三维重建最新技术的研究进展进行整理和归纳。首先,简要总结当前主流的室内空间三维数据采集手段;其次,从室内实景三维模型构建过程中涉及的关键环节出发,从实体要素语义识别和分类、实体要素几何模型生成、空间拓扑特征组织与表达方面对现有方法及其优缺点进行综述;最后,对室内实景三维重建相关研究现存的技术挑战进行分析总结,并对未来研究趋势进行展望。

RIB-NER:基于跨度的中文命名实体识别模型

命名实体识别是自然语言处理领域中诸多下游任务的重要基础。汉语作为重要的国际语言,在许多方面具有独特性。传统上,中文命名实体识别任务模型使用序列标记机制,该机制需要条件随机场捕获标签的依赖性,然而,这种方法容易出现标签的错误分类。针对这个问题,提出基于跨度的命名实体识别模型RIB-NER。首先,以RoBERTa-wwm-ext作为模型嵌入层,提供字符级嵌入,以获得更多的上下文语义信息和词汇信息。其次,利用IDCNN的并行卷积核来增强词之间的位置信息,从而使词与词之间联系更加紧密。同时,在模型中融合BiLSTM网络来获取上下文信息。最后,采用双仿射模型对句子中的开始标记和结束标记评分,使用这些标记探索跨度。在MSRA和Weibo 2个语料库上的实验结果表明,RIB-NER能够较为准确地识别实体边界,并分别获得了95.11%和73.94%的F1值。与传统深度学习相比,有更好的识别效果。

融合领域词典嵌入的航空不安全事件命名实体识别

针对航空不安全事件领域命名实体识别任务,以航空安全信息周报为数据源,分析并构建航空不安全事件命名实体识别数据集和领域词典。为解决传统命名实体识别模型对于捕获领域实体边界性能较差的问题,基于BERT(bidirectional encoder representations from transformers)预训练语言模型提出融合领域词典嵌入的领域语义信息增强的方法。在自建数据集上进行多次对比实验,结果表明:所提出的方法可以进一步提升实体边界的识别率,相较于传统的双向长短期记忆网络-条件随机场(bi-directional long short term memory-conditional random field,BiLSTM-CRF)命名实体识别模型,性能提升约5%。

装配式节点质量信息虚体实化及模型构建

为解决装配式建筑节点质量信息分散,难以进行标准化管理的问题,提出虚体实化理念,将各阶段分散的节点质量信息实体化为BIM模型中的图元对象,并随时间属性关联节点质量过程信息,以实现不同阶段的协同管理。基于虚体实化和BIM技术,定义装配式节点质量信息模型(AJQIM),提出质量实体需求、质量实体监控与质量实体检查基本过程信息模型,并阐述其运作流程、核心功能算法与实现路径。基于Revit平台与MySQL数据库,通过C#二次开发,实现AJQIM的建立。研究结果表明,AJQIM对提高装配式节点质量控制的准确性和完整性具有较高的实用价值。