DPAL-BERT:A Faster and Lighter Question Answering Model

Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems.However,with the constant evolution of algorithms,data,and computing power,the increasing size and complexity of these models have led to increased training costs and reduced efficiency.This study aims to minimize the inference time of such models while maintaining computational performance.It also proposes a novel Distillation model for PAL-BERT(DPAL-BERT),specifically,employs knowledge distillation,using the PAL-BERT model as the teacher model to train two student models:DPAL-BERT-Bi and DPAL-BERTC.This research enhances the dataset through techniques such as masking,replacement,and n-gram sampling to optimize knowledge transfer.The experimental results showed that the distilled models greatly outperform models trained from scratch.In addition,although the distilled models exhibit a slight decrease in performance compared to PAL-BERT,they significantly reduce inference time to just 0.25%of the original.This demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.

Deep Multi-Module Based Language Priors Mitigation Model for Visual Question Answering

The original intention of visual question answering(VQA)models is to infer the answer based on the relevant information of the question text in the visual image,but many VQA models often yield answers that are biased by some prior knowledge,especially the language priors.This paper proposes a mitigation model called language priors mitigation-VQA(LPM-VQA)for the language priors problem in VQA model,which divides language priors into positive and negative language priors.Different network branches are used to capture and process the different priors to achieve the purpose of mitigating language priors.A dynamically-changing language prior feedback objective function is designed with the intermediate results of some modules in the VQA model.The weight of the loss value for each answer is dynamically set according to the strength of its language priors to balance its proportion in the total VQA loss to further mitigate the language priors.This model does not depend on the baseline VQA architectures and can be configured like a plug-in to improve the performance of the model over most existing VQA models.The experimental results show that the proposed model is general and effective,achieving state-of-the-art accuracy in the VQA-CP v2 dataset.

Information Extraction Based on Multi-turn Question Answering for Analyzing Korean Research Trends

Analyzing Research and Development(R&D)trends is important because it can influence future decisions regarding R&D direction.In typical trend analysis,topic or technology taxonomies are employed to compute the popularities of the topics or codes over time.Although it is simple and effective,the taxonomies are difficult to manage because new technologies are introduced rapidly.Therefore,recent studies exploit deep learning to extract pre-defined targets such as problems and solutions.Based on the recent advances in question answering(QA)using deep learning,we adopt a multi-turn QA model to extract problems and solutions from Korean R&D reports.With the previous research,we use the reports directly and analyze the difficulties in handling them using QA style on Information Extraction(IE)for sentence-level benchmark dataset.After investigating the characteristics of Korean R&D,we propose a model to deal with multiple and repeated appearances of targets in the reports.Accordingly,we propose a model that includes an algorithm with two novel modules and a prompt.A newly proposed methodology focuses on reformulating a question without a static template or pre-defined knowledge.We show the effectiveness of the proposed model using a Korean R&D report dataset that we constructed and presented an in-depth analysis of the benefits of the multi-turn QA model.

A survey of deep learning-based visual question answering

With the warming up and continuous development of machine learning,especially deep learning,the research on visual question answering field has made significant progress,with important theoretical research significance and practical application value.Therefore,it is necessary to summarize the current research and provide some reference for researchers in this field.This article conducted a detailed and in-depth analysis and summarized of relevant research and typical methods of visual question answering field.First,relevant background knowledge about VQA(Visual Question Answering)was introduced.Secondly,the issues and challenges of visual question answering were discussed,and at the same time,some promising discussion on the particular methodologies was given.Thirdly,the key sub-problems affecting visual question answering were summarized and analyzed.Then,the current commonly used data sets and evaluation indicators were summarized.Next,in view of the popular algorithms and models in VQA research,comparison of the algorithms and models was summarized and listed.Finally,the future development trend and conclusion of visual question answering were prospected.

A novel approach for agent ontology and its application in question answering

The information integration method of semantic web based on agent ontology(SWAO method) was put forward aiming at the problems in current network environment,which integrates,analyzes and processes enormous web information and extracts answers on the basis of semantics. With SWAO method as the clue,the following technologies were studied:the method of concept extraction based on semantic term mining,agent ontology construction method on account of multi-points and the answer extraction in view of semantic inference. Meanwhile,the structural model of the question answering system applying ontology was presented,which adopts OWL language to describe domain knowledge from where QA system infers and extracts answers by Jena inference engine. In the system testing,the precision rate reaches 86%,and the recalling rate is 93%. The experimental results prove that it is feasible to use the method to develop a question answering system,which is valuable for further study in more depth.

Application of Question and Answering on Virtual Human Dialogue:a Review and Prediction

Nowadays,virtual human(VH) is becoming a hot research topic in virtualization.VH dialogue can be categorized as an application of natural language processing(NLP) technology,since it is relational to question and answering(QA) technologies.In order to integrate these technologies,this paper reviews some important work on VH dialogue,and predicts some research points on the view of QA technologies.

主观题自动评判算法研究综述

在教育教学中,试卷评判是教师获取学生知识点掌握情况的重要途径。然而,试题评分是一个耗时的过程,主观题的评判更需要阅卷人认真、投入、细致地审阅,需要耗费大量精力。要减轻教师工作压力,提高主观题评判的效率,基于人工智能的自动评判技术非常重要,其中主观题的自动评判是难点。随着机器学习和深度学习等技术在自然语言处理领域的发展,主观题自动评判技术有了较大进展。文中将主观题分为常规型和开放型两类进行文献梳理,总结主观题自动评价的标准和公开数据集,归纳涉及的方法和技术路线,并对主观题自动评判技术未来的研究方向进行总结和展望。

Improved Mechanism for Detecting Examinations Impersonations in Public Higher Learning Institutions: Case of the Mwalimu Nyerere Memorial Academy (MNMA)

Currently, most public higher learning institutions in Tanzania rely on traditional in-class examinations, requiring students to register and present identification documents for examinations eligibility verification. This system, however, is prone to impersonations due to security vulnerabilities in current students’ verification system. These vulnerabilities include weak authentication, lack of encryption, and inadequate anti-counterfeiting measures. Additionally, advanced printing technologies and online marketplaces which claim to produce convincing fake identification documents make it easy to create convincing fake identity documents. The Improved Mechanism for Detecting Impersonations (IMDIs) system detects impersonations in in-class exams by integrating QR codes and dynamic question generation based on student profiles. It consists of a mobile verification app, built with Flutter and communicating via RESTful APIs, and a web system, developed with Laravel using HTML, CSS, and JavaScript. The two components communicate through APIs, with MySQL managing the database. The mobile app and web server interact to ensure efficient verification and security during examinations. The implemented IMDIs system was validated by a mobile application which is integrated with a QR codes scanner for capturing codes embedded in student Identity Cards and linking them to a dynamic question generation model. The QG model uses natural language processing (NLP) algorithm and Question Generation (QG) techniques to create dynamic profile questions. Results show that the IMDIs system could generate four challenging profile-based questions within two seconds, allowing the verification of 200 students in 33 minutes by one operator. The IMDIs system also tracks exam-eligible students, aiding in exam attendance and integrates with a Short Message Service (SMS) to report impersonation incidents to a dedicated security officer in real-time. The IMDIs system was tested and found to be 98% secure, 100% convenient, with a 0% false rejection rate and a 2% false acceptance rate, demonstrating its security, reliability, and high performance.

基于大语言模型的智能问答系统在高校中的设计与应用

随着信息技术的迅速发展,智能问答系统已经成为高等教育领域提高教学效率和资源可及性的重要工具。文中探讨了基于大语言模型(LLM)的智能问答系统在高校中的设计与应用。通过分析当前智能问答系统的发展现状和面临的挑战,提出了一个整合了最新自然语言处理技术和人工智能的智能问答系统框架。该系统旨在为学生、教师及其他利益相关者提供快速准确的信息检索和问答服务,涵盖了招生信息、奖学金资讯、职业发展指导、学术辅导等多个方面。通过案例分析,文中展示了系统的设计过程、关键技术、实现挑战及解决策略,旨在为高等教育机构实施智能问答系统提供参考。

表格问答研究综述

表格问答通过自然语言问句直接与表格数据进行交互并得到答案,是智能问答的主要形式之一。近年来,研究人员利用以语义解析为主的技术在该领域开展了深入研究。该文从不同表格类型分类及其问答任务问题定义出发,将表格问答细分为单表单轮、多表单轮、多表多轮式问答三种任务,并系统介绍了各类表格问答任务的数据集及其代表性方法。其次,该文总结了当前主流表格预训练模型的数据构造、输入编码以及预训练目标。最后,探讨当前工作的优势与不足,并分析了未来表格问答的前景与挑战。

问答式林业预训练语言模型ForestBERT

【目的】针对林业文本利用率低、通用领域预训练语言模型对林业知识理解不足以及手动标注数据耗时费力等问题,基于大量林业文本,提出一种融合林业领域知识的预训练语言模型,并通过自动标注训练数据,高效实现林业抽取式问答,为林业决策管理提供智能化信息服务。【方法】首先,基于网络爬虫技术构建包含术语、法律法规和文献3个主题的林业语料库,使用该语料库对通用领域预训练语言模型BERT进行继续预训练,再通过掩码语言模型和下一句预测这2个任务进行自监督学习,使BERT能够有效地学习林业语义信息,得到具有林业文本通用特征的预训练语言模型ForestBERT。然后,对预训练语言模型mT5进行微调,实现样本的自动标注,通过人工校正后,构建包含3个主题共2280个样本的林业抽取式问答数据集。基于该数据集对BERT、RoBERTa、MacBERT、PERT、ELECTRA、LERT 6个通用领域的中文预训练语言模型以及本研究构建的ForestBERT进行训练和验证,以明确ForestBERT的优势。为探究不同主题对模型性能的影响,分别基于林业术语、林业法律法规、林业文献3个主题数据集对所有模型进行微调。将ForestBERT与BERT在林业文献中的问答结果进行可视化比较,以更直观展现ForestBERT的优势。【结果】ForestBERT在林业领域的抽取式问答任务中整体表现优于其他6个对比模型,与基础模型BERT相比,精确匹配(EM)分数和F1分数分别提升1.6%和1.72%,在另外5个模型的平均性能上也均提升0.96%。在各个模型最优划分比例下,ForestBERT在EM上分别优于BERT和其他5个模型2.12%和1.2%,在F1上分别优于1.88%和1.26%。此外,ForestBERT在3个林业主题上也均表现优异,术语、法律法规、文献任务的评估分数分别比其他6个模型平均提升3.06%、1.73%、2.76%。在所有模型中,术语任务表现最佳,F1的平均值达到87.63%,表现较差的法律法规也达到82.32%。在文献抽取式问答任务中,ForestBERT相比BERT可提供更准确、全面的答案。【结论】采用继续预训练的方式增强通用领域预训练语言模型的林业专业知识,可有效提升模型在林业抽取式问答任务中的表现,为林业文本和其他领域的文本处理和应用提供一种新思路。

面向儿科医学试题的答案解析自动推荐方法研究

目的/意义探索并实现儿科医学试题答案的自动化解析,提高试题答案解析编撰效率与质量。方法/过程提出一种隐性语义索引、MC-BERT和CoSENT模型相结合的方法。首先使用基于隐性语义索引的方法和MC-BERT模型从参考文档中抽取多个候选答案解析,然后利用CoSENT模型计算候选解析、试题题干和答案选项之间的相似度,选取相似度最高的候选解析作为最终答案解析。结果/结论该方法答案解析精确率达到72.6%,相较单一方法或模型明显提高查全率和精确率,有效提高了编撰试题答案解析的效率,减轻教育工作者负担,并可为教育研究提供重要的数据支持。

基于变形图匹配的知识图谱多跳问答

知识图谱问答(KGQA)是给定自然语言问题,对问题进行语义理解和解析,进而利用知识图谱进行查询、推理得出答案的过程。但知识图谱通常是不完整的,链接缺失给多跳问答带来许多挑战。许多方法在利用知识图谱嵌入时忽略了重要的路径信息来评估路径和多关系问题之间的相关性;且使用文本语料库也会限制文本增强模型的可扩展性。针对这些现有方法的缺陷,提出了基于变形图匹配的知识图谱问答(DGM-KGQA)模型,该模型同时利用问题和主题实体构建语义子图,与知识图谱的局部结构匹配并找到正确答案。在基准数据集MetaQA上的实验结果验证了DGM-KGQA的有效性,该模型在完整知识图谱上检索到的答案准确率分别比PullNet、EmbedKGQA增加了4.2%、0.8%;在完整度仅有一半的知识图谱上检索到的答案准确率分别比PullNet、EmbedKGQA增加了11.1%、0.5%。实验证明提出的变形图匹配模型能够有效地增强知识图谱的关联性及多跳问答的答案准确率。

基于视觉问答的施工过程视觉语言理解

监控系统在施工现场的广泛应用创造大量数据,但受限于有限的分析方法,未能充分体现这些数据的信息价值。自然语言是最直接的表达方式,在施工管理中最便于使用和理解。使用多模态视觉语言模型,对通过施工自然语言问答获取施工现场信息、进行施工智能管理有巨大帮助,然而目前针对施工现场的多模态研究仍然不足。为此,建立施工视觉问答数据集,经过数据增强后,包含超过19000条问答对及对应图像,用于训练适用于施工现场的视觉问答模型。提出基于多头注意力机制及预训练视觉Transformer的施工问答模型,该模型在测试集中取得约79.3%的准确率,表明多模态视觉语言理解在获取施工信息层面具有巨大潜力,可为施工智能管理提供有效的信息基础。

可解释的视觉问答研究进展

在视觉问答(VQA)任务中,“可解释”是指在特定的任务中通过各种方法去解释模型为什么有效。现有的一些VQA模型因为缺乏可解释性导致模型无法保证在生活中能安全使用,特别是自动驾驶和医疗相关的领域,将会引起一些伦理道德问题,导致无法在工业界落地。主要介绍视觉问答任务中的各种可解释性实现方式,并分为了图像解释、文本解释、多模态解释、模块化解释和图解释五类,讨论了各种方法的特点并对其中的一些方法进行了细分。除此之外,还介绍了一些可以增强可解释性的视觉问答数据集,这些数据集主要通过结合外部知识库、标注图片信息等方法来增强可解释性。对现有常用的视觉问答可解释方法进行了总结,最后根据现有视觉问答任务中可解释性方法的不足提出了未来的研究方向。

融入软掩码机制增强数值表示的表格-文本混合问答

表格-文本混合问答需要从异质数据中进行数值推理得到答案,当前的研究将问题、表格、文本拼接作为输入,但其中包含太多不相关的数值和文本会降低模型的性能.使用硬掩码机制将噪音去除以增强正确的数值表示会产生错误传播问题,本文提出一种新的软掩码机制对原始输入表示进行缩放,从而增强正确的数值表示,同时减轻错误传播问题,并且该机制可以灵活地运用到各种模型以及任务中.本文在FinQA、ConvFinQA和MultiHiertt数据集上进行实验,结果表明通过软掩码机制增强数值表示可显著提升模型的性能(+1.27/+1.65Exe/Prog Acc、+3.09/+2.96Exe/Prog Acc和+5.29/+3.45EM/F1).本文还通过消融实验分析软掩码相对于硬掩码的优势,以及不同软掩码向量的影响,并讨论了当前表格-文本混合问答的局限性与未来方向.

文本视觉问答综述

传统视觉问答(VQA)大多只关注图像中的视觉对象信息,忽略了对图像中文本信息的关注。文本视觉问答(TextVQA)除了视觉信息外还关注了图像中的文本信息,能够更加准确并高效地回答问题。近年来,TextVQA已经成为多模态领域的研究热点,在自动驾驶、场景理解等包含文本信息的场景中有重要的应用前景。阐述TextVQA的概念以及存在的问题与挑战,从方法、数据集、未来研究方向等方面对TextVQA任务进行系统性的分析。总结现有的TextVQA研究方法,并将其归纳为3个阶段,分别为特征提取阶段、特征融合阶段和答案预测阶段。根据融合阶段使用方法的不同,从简单注意力方法、基于Transformer方法和基于预训练方法这3个方面对TextVQA方法进行阐述,分析对比不同方法的特点以及在公开数据集中的表现。介绍TextVQA领域4种常用的公共数据集,并对它们的特点和评价指标进行分析。在此基础上,探讨当前TextVQA任务中存在的问题与挑战,并对该领域未来的研究方向进行展望。

不同大型语言模型与不同水平医学专业人士回答眼科问题的对比研究

目的:评估3种不同的大型语言模型(LLM,包括GPT-3.5、GPT-4和PaLM2)在回答眼科专业问题中的表现并与3种不同水平的专业人群(医学本科生、医学硕士、主治医师)进行比较。方法:分别对三种不同的LLM和3种不同水平的专业人群(包括了本科生9名,专业型研究生6名,主治医师3名)进行一项由100道眼科单项选择题组成的测试,问题涵盖了眼科基础知识、临床知识、眼科检查诊断方法以及眼病相关治疗手段。从平均得分、答题稳定性和答题自信心等方面综合评估LLM的性能并与人类组进行比较。结果:在平均测试得分中,每个LLM都在总体上优于本科生(GPT-4:56分,GPT-3.5:42分,PaLM2:47分,本科生:40分),其中GPT-3.5、PaLM2略低于硕士水平(硕士:51分),而GPT-4则表现出与主治医师相当的水平(主治医师:62分)。另外,GPT-4表现出明显高于GPT-3.5和PaLM2的答题稳定性和答题自信心。结论:以GPT-4为代表的LLM在眼科领域表现的较为出色,LLM模型可为临床医生和医学教育进行临床决策及教学辅助。

旅游领域意图识别和槽位填充联合建模方法研究

构建了基于BERT的双向连接模式BERT-based Bi-directional Association Model(BBAM)以实现在意图识别和槽位填充之间建立双向关系的目标,来实现意图识别与槽位填充的双向关联,融合两个任务的上下文信息,对意图识别与槽位填充两个任务之间的联系进行深度挖掘,从而优化问句理解的整体性能.为了验证模型在旅游领域中的实用性和有效性,通过远程监督和人工校验构建了旅游领域问句数据集TFQD(Tourism Field Question Dataset),BBAM模型在此数据集上的槽填充任务F 1值得分为95.21%,意图分类准确率(A)为96.71%,整体识别准确率(A_(sentence))高达89.62%,显著优于多种基准模型.所提出的模型在ATIS和Snips两个公开数据集上与主流联合模型进行对比实验后,结果表明其具备一定的泛化能力.

基于图神经网络的问答系统

针对目前问答模型对文本语义理解能力不足、缺少常识性知识,且无法有效利用现存海量文本信息的现状,研究一种基于图神经网络的问答系统。通过预训练技术和图注意力算法的有效结合,融合来自常识知识库中的结构化知识,通过准确的知识推理获得对文本深层次语义的理解,最终作出正确的回答。在对话文本和抽象语义文本等数据集上进行的一系列对比实验验证了该问答系统的有效性,表明其具备在对话文本及抽象语义概念上的理解能力。