MKEAH:Multimodal knowledge extraction and accumulation based on hyperplane embedding for knowledge-based visual question answering

Background External knowledge representations play an essential role in knowledge-based visual question and answering to better understand complex scenarios in the open world.Recent entity-relationship embedding approaches are deficient in representing some complex relations,resulting in a lack of topic-related knowledge and redundancy in topic-irrelevant information.Methods To this end,we propose MKEAH:Multimodal Knowledge Extraction and Accumulation on Hyperplanes.To ensure that the lengths of the feature vectors projected onto the hyperplane compare equally and to filter out sufficient topic-irrelevant information,two losses are proposed to learn the triplet representations from the complementary views:range loss and orthogonal loss.To interpret the capability of extracting topic-related knowledge,we present the Topic Similarity(TS)between topic and entity-relations.Results Experimental results demonstrate the effectiveness of hyperplane embedding for knowledge representation in knowledge-based visual question answering.Our model outperformed state-of-the-art methods by 2.12%and 3.24%on two challenging knowledge-request datasets:OK-VQA and KRVQA,respectively.Conclusions The obvious advantages of our model in TS show that using hyperplane embedding to represent multimodal knowledge can improve its ability to extract topic-related knowledge.

PAL-BERT:An Improved Question Answering Model

In the field of natural language processing(NLP),there have been various pre-training language models in recent years,with question answering systems gaining significant attention.However,as algorithms,data,and computing power advance,the issue of increasingly larger models and a growing number of parameters has surfaced.Consequently,model training has become more costly and less efficient.To enhance the efficiency and accuracy of the training process while reducing themodel volume,this paper proposes a first-order pruningmodel PAL-BERT based on the ALBERT model according to the characteristics of question-answering(QA)system and language model.Firstly,a first-order network pruning method based on the ALBERT model is designed,and the PAL-BERT model is formed.Then,the parameter optimization strategy of the PAL-BERT model is formulated,and the Mish function was used as an activation function instead of ReLU to improve the performance.Finally,after comparison experiments with traditional deep learning models TextCNN and BiLSTM,it is confirmed that PALBERT is a pruning model compression method that can significantly reduce training time and optimize training efficiency.Compared with traditional models,PAL-BERT significantly improves the NLP task’s performance.

Operational requirements analysis method based on question answering of WEKG

The weapon and equipment operational requirement analysis(WEORA) is a necessary condition to win a future war,among which the acquisition of knowledge about weapons and equipment is a great challenge. The main challenge is that the existing weapons and equipment data fails to carry out structured knowledge representation, and knowledge navigation based on natural language cannot efficiently support the WEORA. To solve above problem, this research proposes a method based on question answering(QA) of weapons and equipment knowledge graph(WEKG) to construct and navigate the knowledge related to weapons and equipment in the WEORA. This method firstly constructs the WEKG, and builds a neutral network-based QA system over the WEKG by means of semantic parsing for knowledge navigation. Finally, the method is evaluated and a chatbot on the QA system is developed for the WEORA. Our proposed method has good performance in the accuracy and efficiency of searching target knowledge, and can well assist the WEORA.

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.

ANSWER模型评估新疆咸水灌溉棉花产量与效益

利用咸水或微咸水进行农田灌溉是缓解中国新疆地区农业水资源供需矛盾从而保障当地棉花产业可持续发展的主要途径之一。为了明确不同咸水灌溉措施对棉花产量及经济效益的影响,该研究通过2 a的棉花膜下滴灌大田试验和文献检索获取了新疆9个不同试验地点的土壤、作物及灌溉等数据资料,评估作物产量-水盐胁迫响应分析模型(ANalytical Salt WatER,ANSWER)在新疆棉花产量评估中的适用性和可靠性,并结合经济收支平衡方法,模拟分析不同咸水灌溉措施(包括不同灌溉定额和灌溉水电导率的组合)对棉花产量与经济效益的影响。采用决定系数(R2)、均方根误差(root mean squared error,RMSE)、相对均方根误差(relative root mean squared error,RRMSE)评价模型精度。结果表明,在9个不同试验地点,ANSWER模型均可较准确地估算棉花的相对产量,其估算值与实测值之间的R^(2)≥0.54,RMSE≤0.14,RRMSE≤0.16;不同试验地点,优化获得的各个模型生物参数(与棉花根系吸水的水盐胁迫响应相关的参数)差异较小,变异系数的绝对值处于0.08~0.37之间;基于不同试验地点优化的各生物参数均值估算各地的棉花相对产量,其与实测值仍然吻合良好(R^(2)为0.59,RMSE为0.06,RRMSE为0.07);此外,当灌溉水电导率一定时,棉花净收益随灌溉定额增加呈先增后降的趋势,净收益达到峰值所需的灌溉定额随灌溉水电导率升高而迅速增加;当灌溉水电导率不大于10 dS/m时,通过加大供水量均可获得与淡水灌溉相当的净收益。研究可为新疆地区棉花产量与效益评估以及咸水资源合理开发利用提供理论依据。

Analysis of community question-answering issues via machine learning and deep learning:State-of-the-art review

Over the last couple of decades,community question-answering sites(CQAs)have been a topic of much academic interest.Scholars have often leveraged traditional machine learning(ML)and deep learning(DL)to explore the ever-growing volume of content that CQAs engender.To clarify the current state of the CQA literature that has used ML and DL,this paper reports a systematic literature review.The goal is to summarise and synthesise the major themes of CQA research related to(i)questions,(ii)answers and(iii)users.The final review included 133 articles.Dominant research themes include question quality,answer quality,and expert identification.In terms of dataset,some of the most widely studied platforms include Yahoo!Answers,Stack Exchange and Stack Overflow.The scope of most articles was confined to just one platform with few cross-platform investigations.Articles with ML outnumber those with DL.Nonetheless,the use of DL in CQA research is on an upward trajectory.A number of research directions are proposed.

Expert Recommendation in Community Question Answering via Heterogeneous Content Network Embedding

ExpertRecommendation(ER)aims to identify domain experts with high expertise and willingness to provide answers to questions in Community Question Answering(CQA)web services.How to model questions and users in the heterogeneous content network is critical to this task.Most traditional methods focus on modeling questions and users based on the textual content left in the community while ignoring the structural properties of heterogeneous CQA networks and always suffering from textual data sparsity issues.Recent approaches take advantage of structural proximities between nodes and attempt to fuse the textual content of nodes for modeling.However,they often fail to distinguish the nodes’personalized preferences and only consider the textual content of a part of the nodes in network embedding learning,while ignoring the semantic relevance of nodes.In this paper,we propose a novel framework that jointly considers the structural proximity relations and textual semantic relevance to model users and questions more comprehensively.Specifically,we learn topology-based embeddings through a hierarchical attentive network learning strategy,in which the proximity information and the personalized preference of nodes are encoded and preserved.Meanwhile,we utilize the node’s textual content and the text correlation between adjacent nodes to build the content-based embedding through a meta-context-aware skip-gram model.In addition,the user’s relative answer quality is incorporated to promote the ranking performance.Experimental results show that our proposed framework consistently and significantly outperforms the state-of-the-art baselines on three real-world datasets by taking the deep semantic understanding and structural feature learning together.The performance of the proposed work is analyzed in terms of MRR,P@K,and MAP and is proven to be more advanced than the existing methodologies.

ALBERT with Knowledge Graph Encoder Utilizing Semantic Similarity for Commonsense Question Answering

Recently,pre-trained language representation models such as bidirec-tional encoder representations from transformers(BERT)have been performing well in commonsense question answering(CSQA).However,there is a problem that the models do not directly use explicit information of knowledge sources existing outside.To augment this,additional methods such as knowledge-aware graph network(KagNet)and multi-hop graph relation network(MHGRN)have been proposed.In this study,we propose to use the latest pre-trained language model a lite bidirectional encoder representations from transformers(ALBERT)with knowledge graph information extraction technique.We also propose to applying the novel method,schema graph expansion to recent language models.Then,we analyze the effect of applying knowledge graph-based knowledge extraction techniques to recent pre-trained language models and confirm that schema graph expansion is effective in some extent.Furthermore,we show that our proposed model can achieve better performance than existing KagNet and MHGRN models in CommonsenseQA 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.

Improved Blending Attention Mechanism in Visual Question Answering

Visual question answering(VQA)has attracted more and more attention in computer vision and natural language processing.Scholars are committed to studying how to better integrate image features and text features to achieve better results in VQA tasks.Analysis of all features may cause information redundancy and heavy computational burden.Attention mechanism is a wise way to solve this problem.However,using single attention mechanism may cause incomplete concern of features.This paper improves the attention mechanism method and proposes a hybrid attention mechanism that combines the spatial attention mechanism method and the channel attention mechanism method.In the case that the attention mechanism will cause the loss of the original features,a small portion of image features were added as compensation.For the attention mechanism of text features,a selfattention mechanism was introduced,and the internal structural features of sentences were strengthened to improve the overall model.The results show that attention mechanism and feature compensation add 6.1%accuracy to multimodal low-rank bilinear pooling network.

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.

基于知识图谱多跳推理的中文矿物知识问答方法与系统

已有相关矿物数据库用于存储和查询相关矿物知识,常用的搜索引擎也可以对矿物知识进行查询,但无法回答用自然语言进行提问的矿物问题,查询返回的答案需要进一步筛选。亦有基于知识图谱进行矿物知识问答的相关研究,但只能回答涉及知识图谱中一个三元组的简单问题,无法回答涉及多个三元组的多跳复杂问题。为此,本文提出基于知识图谱多跳推理的矿物复杂知识问答方法,采用ComplEx模型将矿物实体、关系和问句表示为复数向量,以更好地获取相互之间的语义及推理关系。输入矿物问句后,通过Bert-LSTM-CRF获取其中心词,采用基于编辑距离及分词的方法获得中心词的候选实体集合,然后采用全连接网络确定最相关的实体作为推理起点,与矿物问句拼接后通过全连接网络获得当前跳的最相关关系。根据当前跳的起始实体及最相关关系,在矿物知识图谱中获得另一实体作为下一跳的推理起点,并将下一跳的问句更新为原问句,与当前跳最相关关系拼接,以将当前跳的推理信息带入到下一跳推理中,直到获得的最相关推理关系为预定义的结束标识符,推理结束,返回最后一跳的实体为答案,并给出推理路径。采用Python语言,在Tensorflow框架下实现了本文提出的矿物复杂知识问答并与相关模型进行对比,证明了本文方法的有效性。采用前后端分离架构,使用RESTful API、React、Ajax、echarts和Flask等框架和技术,开发了基于知识图谱多跳推理的矿物复杂知识问答系统,为矿物知识获取及相关地质研究提供了平台和工具。

旅游自动问答系统中多任务问句分类研究

目前旅游产业信息化建设需要构建旅游自动问答系统,其中问句分类是问答系统的重要组成部分,传统问句类别体系角度单一,且传统分类模型对不平衡的问句数据集表现欠佳。针对这一问题,该文从问题主题和问句答案类型两个角度构建了旅游领域的问句类别体系架构,并提出多任务问句分类模型MT-Bert,在BERT上进行多任务训练,并加入自注意力机制,使用Softmax分类器,并设计了多任务融合损失函数。在山西旅游数据集的结果表明,MT-Bert在两种类别体系的微平均F1值分别为97.6%、91.7%,且避免了非平衡数据的预测失败问题,可以有效处理非平衡数据。

破解历史周期率“两个答案”的辩证思考

中国共产党在跳出治乱兴衰历史周期率问题上长期求解,先后得出了人民监督的“第一个答案”和自我革命的“第二个答案”,回应了马克思主义政党如何加强自身建设和实现长期执政的重大时代课题,是对中国共产党执政规律、自身建设规律和人类社会发展规律的科学把握。“两个答案”并非孤立存在,而是相互联系、相互影响、相互制约的有机统一体。二者虽提出有先后,但同根同源、实践同步;虽主体有差异,但旨归统一、立场一致;虽内容有侧重,但任务趋同、目标相通;虽动因分内外,但机制互补、辩证互成。以辩证思维对破解历史周期率“两个答案”之间的关系进行深入思考,坚持“人民监督”与强化“自我革命”统筹推进,既是巩固党的长期执政地位的内在要求,也是走好新的赶考之路的必然选择。

从“第二个结合”看“第二个答案”:习近平总书记关于党的自我革命的重要思想的理论内涵与实践进路

党的十八大以来,习近平总书记带领全党以前所未有的决心与力度推进全面从严治党,创造性提出一系列具有原创性、标志性的新理念新思想新战略,形成了习近平总书记关于党的自我革命的重要思想。这一重要思想是我们党坚持把马克思主义基本原理同中国具体实际相结合、同中华优秀传统文化相结合推进理论创新取得的新成果,是习近平新时代中国特色社会主义思想科学体系的重要组成部分。从中西文明视角考察“革命”到“自我革命”概念史生成源流,“革命”一词本义就体现了“兴也勃焉、亡也忽焉”的历史周期率,与破除旧的政治上层建筑的社会运动,实现新的社会建设运动的西方资产阶级传统“革命”观念不同,“自我革命”承接了马克思主义重构经济结构的内涵,更强调革命主体从自我内因角度出发接受革命性锻造。“党的自我革命”与中华优秀传统文化中蕴含的“革故鼎新”“自省克己”“民为邦本”“正身率下”思想与内涵高度契合,勇于自我革命是中国共产党最鲜明的品格,体现了中国共产党深厚的文化自信。习近平总书记在二十届中央纪委三次全会上发表重要讲话,明确提出“九个以”的实践要求,对持续发力、纵深推进反腐败斗争作出战略部署。这“九个以”的实践要求,既有宏观层面的目标任务、顶层设计,也有落细落实、重点突出的方式方法;既有认识论,又有方法论。我们从“第二个结合”看“第二个答案”,领悟党的自我革命的重要思想理论内涵与实践进路,要从“第二个结合”视角,把握习近平总书记关于党的自我革命的重要思想所蕴含的重大创新观点、科学方法和重要战略部署,更加自觉主动地以伟大自我革命引领伟大社会革命。

面向小样本抽取式问答的多标签语义校准方法

小样本抽取式问答任务旨在利用文章给定的上下文片段,抽取出真实的答案片段。其基线模型采用的方法只针对跨度进行学习,缺乏对全局语义信息的利用,在含有多组不同重复跨度的实例中存在着理解偏差等问题。为了解决上述问题,该文利用不同层级的语义提出了一种面向小样本抽取式问答任务的多标签语义校准方法。采用包含全局语义信息的头标签和基线模型中的特殊字符构成多标签进行语义融合,并利用语义融合门来控制全局信息流的引入,将全局语义信息融合到特殊字符的语义信息中。然后,利用语义筛选门对新融入的全局语义信息和该特殊字符的原有语义信息进行保留与更替,实现对标签偏差语义的校准。在8个小样本抽取式问答数据集中的56组实验结果表明:该方法在评价指标F1值上均明显优于基线模型,证明了所提方法的有效性和先进性。

一种面向中文自动问答的注意力交互深度学习模型

随着互联网、大数据的飞速发展,以深度神经网络(DNN)为代表的人工智能技术迎来了黄金发展时期,自动问答作为人工智能领域的一个重要分支,也得到越来越多学者的关注。现有网络模型可以提取问题或答案的语义特征,但其一方面忽略了问题与答案之间的语义联系,另一方面也不能从整体上把握问题或答案内部所有字符之间的潜在联系。基于此,提出了两种不同形式的注意力交互模块,即互注意力交互模块和自注意力交互模块,并设计出一套基于所提注意力交互模块的深度学习模型,用于证明该注意力交互模块的有效性。首先将问题和答案中的每个字符映射成固定长度的向量,分别得到问题和答案对应的字嵌入矩阵;然后将字嵌入矩阵送入注意力交互模块,得到综合考虑问题与答案所有字符之后的字嵌入矩阵,并与之前的字嵌入矩阵相加,送入深度神经网络模块,用于提取问题与答案的语义特征;最后得到问题与答案的向量表示并计算两者之间的相似度。实验结果表明,所提模型的Top-1准确度较主流深度学习模型最高提升了3.55%,证明了所提注意力交互模块对于改善上述问题的有效性。

反绎学习支持下的自动问答及其应用

自动问答技术可以为用户提供快速且准确的信息检索和问题解答服务。然而,目前常见方法生成的答案存在不准确和不完整的问题,以及实体识别和关系抽取效果不准确,且答案不够自然。为此,提出基于反绎学习的自动问答方法,使用基于知识图谱的问答推理优化基于生成的问答,进一步从整体的反绎学习框架角度来优化实体识别和关系抽取方法,并将所提方法应用于《数据结构》课程的学习。结果表明,基于反绎学习的自动问答方法,可以改进基于生成的问答和基于知识图谱的问答两者的不足,提高问答系统的准确性。

党以自我革命跳出历史周期率的逻辑支撑和体系保障

能否跳出历史周期率是关系党的生死存亡和国家前途命运的重大问题。经过百余年的不懈探索,中国共产党成功找到跳出历史周期率的“第二个答案”,即自我革命。党以自我革命跳出历史周期率的逻辑支撑在于马克思主义赋予了党敢于自我革命的内在品质、党能够认识与把握“三大规律”、党积累了以自我革命保持先进性的丰富经验。新时代深入推进党的自我革命,需要坚持和完善党的领导制度体系,健全全面从严治党体系,健全学习贯彻党的创新理论的制度机制,构建自我革命、民主监督与依法治国相结合的治理体系,完善自我革命与社会革命协同推进体系。

面向机器阅读理解的边界感知方法

针对现有的基于预训练语言模型的答案获取方法存在预测边界不够准确的问题,提出一种面向片段抽取式机器阅读理解(MRC)的边界感知方法。首先,在问题输入阶段引入特殊字符标记问题边界,通过增强问题语义信息的方式实现对问题边界的感知;其次,在答案预测阶段,构建答案边界回归器,实现感知的问题边界语义信息与输出的预测答案边界语义信息的语义交互;最后,通过交互后的语义信息进一步调整存在偏差的预测答案边界,实现对预测答案的校准。实验结果表明,与SpanBERT(Span-based Bidirectional Encoder Representation from Transformers)相比,该方法在公共数据集SQuAD(Stanford Question Answering Dataset)1.1上的F1值提升了0.2个百分点、精确匹配(EM)值提升了0.9个百分点;在HotpotQA(Hotpot Question Answering)数据集上的F1值和EM值都提升了0.7个百分点;在NewsQA(News Question Answering)数据集上的F1值提升了2.8个百分点、EM值提升了3.3个百分点。可见,该方法能有效增强对问题边界信息的感知并且实现对预测答案边界的校准,有利于更好地理解和分析文本数据,在智能问答、智能客服等领域的应用中提高系统的准确性。