共查询到20条相似文献，搜索用时 15 毫秒
1.
《Information processing & management》2023,60(3):103295
The appearance attribute and pose are two important and complementary features, so integrating them can effectively alleviate the impact of misalignment and occlusion on re-identification. In this paper, we deeply investigate the inner relation between attribute features and the spatial semantic relation between key-point region features of the pose in a person image and propose a person re-identification method based on discriminative feature mining with relation regularization. Firstly, an attribute relation detector based on nonlinear graph convolution is built on mining the inner correlation between attribute features of a person, providing relational attribute features for more effectively distinguishing persons with a similar appearance. Then, we construct a hierarchical pose pyramid to model the multi-grained semantic features of key-point regions of the pose and propose intra-graph and cross-graph node relation information propagation structures to infer the spatial semantic relation between node features within-graph and between-graph. This module is robust to complex pose changes and can suppress noise background redundancy caused by inaccurate key point detection and occlusion. Finally, a refined feature model is proposed to effectively fuse the global appearance feature with the relational attribute and multi-grained pose features, thus providing a more discriminative fusion feature for person re-identification. Many experiments on three large-scale datasets verify the effectiveness and state-of-the-art performance of the proposed method. 相似文献
2.
《Information processing & management》2020,57(6):102309
Effectively detecting supportive knowledge of answers is a fundamental step towards automated question answering. While pre-trained semantic vectors for texts have enabled semantic computation for background-answer pairs, they are limited in representing structured knowledge relevant for question answering. Recent studies have shown interests in enrolling structured knowledge graphs for text processing, however, their focus was more on semantics than on graph structure. This study, by contrast, takes a special interest in exploring the structural patterns of knowledge graphs. Inspired by human cognitive processes, we propose novel methods of feature extraction for capturing the local and global structural information of knowledge graphs. These features not only exhibit good indicative power, but can also facilitate text analysis with explainable meanings. Moreover, aiming to better combine structural and semantic evidence for prediction, we propose a Neural Knowledge Graph Evaluator (NKGE) which showed superior performance over existing methods. Our contributions include a novel set of interpretable structural features and the effective NKGE for compatibility evaluation between knowledge graphs. The methods of feature extraction and the structural patterns indicated by the features may also provide insights for related studies in computational modeling and processing of knowledge. 相似文献
3.
《Information processing & management》2020,57(6):102359
Text summarization is a process of generating a brief version of documents by preserving the fundamental information of documents as much as possible. Although most of the text summarization research has been focused on supervised learning solutions, there are a few datasets indeed generated for summarization tasks, and most of the existing summarization datasets do not have human-generated goal summaries which are vital for both summary generation and evaluation. Therefore, a new dataset was presented for abstractive and extractive summarization tasks in this study. This dataset contains academic publications, the abstracts written by the authors, and extracts in two sizes, which were generated by human readers in this research. Then, the resulting extracts were evaluated to ensure the validity of the human extract production process. Moreover, the extractive summarization problem was reinvestigated on the proposed summarization dataset. Here the main point taken into account was to analyze the feature vector to generate more informative summaries. To that end, a comprehensive syntactic feature space was generated for the proposed dataset, and the impact of these features on the informativeness of the resulting summary was investigated. Besides, the summarization capability of semantic features was experienced by using GloVe and word2vec embeddings. Finally, the use of ensembled feature space, which corresponds to the joint use of syntactic and semantic features, was proposed on a long short-term memory-based neural network model. ROUGE metrics evaluated the model summaries, and the results of these evaluations showed that the use of the proposed ensemble feature space remarkably improved the single-use of syntactic or semantic features. Additionally, the resulting summaries of the proposed approach on ensembled features prominently outperformed or provided comparable performance than summaries obtained by state-of-the-art models for extractive summarization. 相似文献
4.
Extracting semantic relationships between entities from text documents is challenging in information extraction and important for deep information processing and management. This paper investigates the incorporation of diverse lexical, syntactic and semantic knowledge in feature-based relation extraction using support vector machines. Our study illustrates that the base phrase chunking information is very effective for relation extraction and contributes to most of the performance improvement from syntactic aspect while current commonly used features from full parsing give limited further enhancement. This suggests that most of useful information in full parse trees for relation extraction is shallow and can be captured by chunking. This indicates that a cheap and robust solution in relation extraction can be achieved without decreasing too much in performance. We also demonstrate how semantic information such as WordNet, can be used in feature-based relation extraction to further improve the performance. Evaluation on the ACE benchmark corpora shows that effective incorporation of diverse features enables our system outperform previously best-reported systems. It also shows that our feature-based system significantly outperforms tree kernel-based systems. This suggests that current tree kernels fail to effectively explore structured syntactic information in relation extraction. 相似文献
5.
Shallow semantic parsing assigns a simple structure (such as WHO did WHAT to WHOM, WHEN, WHERE, WHY, and HOW) to each predicate in a sentence. It plays a critical role in event-based information extraction and thus is important for deep information processing and management. This paper proposes a tree kernel method for a particular shallow semantic parsing task, called semantic role labeling (SRL), with an enriched parse tree structure. First, a new tree kernel is presented to effectively capture the inherent structured knowledge in a parse tree by enabling the standard convolution tree kernel with context-sensitiveness via considering ancestral information of substructures and approximate matching via allowing insertion/deletion/substitution of tree nodes in the substructures. Second, an enriched parse tree structure is proposed to both well preserve the necessary structured information and effectively avoid noise by differentiating various portions of the parse tree structure. Evaluation on the CoNLL’2005 shared task shows that both the new tree kernel and the enriched parse tree structure contribute much in SRL and our tree kernel method significantly outperforms the state-of-the-art tree kernel methods. Moreover, our tree kernel method is proven rather complementary to the state-of-the-art feature-based methods in that it can better capture structural parse tree information. 相似文献
6.
《Information processing & management》2020,57(6):102344
Relation classification is one of the most fundamental tasks in the area of cross-media, which is essential for many practical applications such as information extraction, question&answer system, and knowledge base construction. In the cross-media semantic retrieval task, in order to meet the needs of cross-media uniform representation and semantic analysis, it is necessary to analyze the semantic potential relationship and construct semantic-related cross-media knowledge graph. The relationship classification technology is an important part of solving semantic correlation classification. Most of existing methods regard relation classification as a multi-classification task, without considering the correlation between different relationships. However, two relationships in the opposite directions are usually not independent of each other. Hence, this kind of relationships are easily confused in the traditional way. In order to solve the problem of confusing the relationships of the same semantic with different entity directions, this paper proposes a neural network fusing discrimination information for relation classification. In the proposed model, discrimination information is used to distinguish the relationship of the same semantic with different entity directions, the direction of entity in space is transformed into the direction of vector in mathematics by the method of entity vector subtraction, and the result of entity vector subtraction is used as discrimination information. The model consists of three modules: sentence representation module, relation discrimination module and discrimination fusion module. Moreover, two fusion methods are used for feature fusion. One is a Cascade-based feature fusion method, and another is a feature fusion method based on convolution neural network. In addition, this paper uses the new function added by cross-entropy function and deformed Max-Margin function as the loss function of the model. The experimental results show that the proposed discriminant feature is effective in distinguishing confusing relationships, and the proposed loss function can improve the performance of the model to a certain extent. Finally, the proposed model achieves 84.8% of the F1 value without any additional features or NLP analysis tools. Hence, the proposed method has a promising prospect of being incorporated in various cross-media systems. 相似文献
7.
[目的/意义]实体语义关系分类是信息抽取重要任务之一，将非结构化文本转化成结构化知识，是构建领域本体、知识图谱、开发问答系统、信息检索系统的基础工作。[方法/过程]本文详细梳理了实体语义关系分类的发展历程，从技术方法、应用领域两方面回顾和总结了近5年国内外的最新研究成果，并指出了研究的不足及未来的研究方向。[结果/结论]热门的深度学习方法抛弃了传统浅层机器学习方法繁琐的特征工程，自动学习文本特征，实验发现，在神经网络模型中融入词法、句法特征、引入注意力机制能有效提升关系分类性能。 相似文献
8.
基于改进特征提取及聚类的网络评论挖掘研究 总被引：1，自引：0，他引：1
[目的/意义]针对信息过载条件下中文网络产品评论中特征提取性能低以及特征聚类中初始中心点的选取问题。[方法/过程]本研究提出采用基于权重的改进Apriori算法产生候选产品特征集合,再根据独立支持度、频繁项名词非特征规则及基于网络搜索引擎的PMI算法对候选产品特征集合进行过滤。并以基于HowNet的语义相似度和特征观点共现作为衡量产品特征之间关联程度的特征,提出一种改进K-means聚类算法对产品特征进行聚类。[结果/结论]实验结果表明,在特征提取阶段,查准率为69%,查全率为92.64%,综合值达到79.07%。在特征聚类阶段,本文提出的改进K-means算法相对传统算法具有更优的挖掘性能。 相似文献
9.
《Information processing & management》2023,60(4):103350
Knowledge graphs are sizeable graph-structured knowledge with both abstract and concrete concepts in the form of entities and relations. Recently, convolutional neural networks have achieved outstanding results for more expressive representations of knowledge graphs. However, existing deep learning-based models exploit semantic information from single-level feature interaction, potentially limiting expressiveness. We propose a knowledge graph embedding model with an attention-based high-low level features interaction convolutional network called ConvHLE to alleviate this issue. This model effectively harvests richer semantic information and generates more expressive representations. Concretely, the multilayer convolutional neural network is utilized to fuse high-low level features. Then, features in fused feature maps interact with other informative neighbors through the criss-cross attention mechanism, which expands the receptive fields and boosts the quality of interactions. Finally, a plausibility score function is proposed for the evaluation of our model. The performance of ConvHLE is experimentally investigated on six benchmark datasets with individual characteristics. Extensive experimental results prove that ConvHLE learns more expressive and discriminative feature representations and has outperformed other state-of-the-art baselines over most metrics when addressing link prediction tasks. Comparing MRR and Hits@1 on FB15K-237, our model outperforms the baseline ConvE by 13.5% and 16.0%, respectively. 相似文献
10.
《Information processing & management》2023,60(2):103159
With the development of 3D technology and the increase in 3D models, 2D image-based 3D model retrieval tasks have drawn increased attention from scholars. Previous works align cross-domain features via adversarial domain alignment and semantic alignment. However, the extracted features of previous methods are disturbed by the residual domain-specific features, and the lack of labels for 3D models makes the semantic alignment challenging. Therefore, we propose disentangled feature learning associated with enhanced semantic alignment to address these problems. On one hand, the disentangled feature learning enables decoupling the twisted raw features into the isolated domain-invariant and domain-specific features, and the domain-specific features will be dropped while performing adversarial domain alignment and semantic alignment to acquire domain-invariant features. On the other hand, we mine the semantic consistency by compacting each 3D model sample and its nearest neighbors to further enhance semantic alignment for unlabeled 3D model domain. We give comprehensive experiments on two public datasets, and the results demonstrate the superiority of the proposed method. Especially on MI3DOR-2 dataset, our method outperforms the current state-of-the-art methods with gains of 2.88% for the strictest retrieval metric NN. 相似文献
11.
《Information processing & management》2023,60(1):103120
Multimodal fake news detection methods based on semantic information have achieved great success. However, these methods only exploit the deep features of multimodal information, which leads to a large loss of valid information at the shallow level. To address this problem, we propose a progressive fusion network (MPFN) for multimodal disinformation detection, which captures the representational information of each modality at different levels and achieves fusion between modalities at the same level and at different levels by means of a mixer to establish a strong connection between the modalities. Specifically, we use a transformer structure, which is effective in computer vision tasks, as a visual feature extractor to gradually sample features at different levels and combine features obtained from a text feature extractor and image frequency domain information at different levels for fine-grained modeling. In addition, we design a feature fusion approach to better establish connections between modalities, which can further improve the performance and thus surpass other network structures in the literature. We conducted extensive experiments on two real datasets, Weibo and Twitter, where our method achieved 83.3% accuracy on the Twitter dataset, which has increased by at least 4.3% compared to other state-of-the-art methods. This demonstrates the effectiveness of MPFN for identifying fake news, and the method reaches a relatively advanced level by combining different levels of information from each modality and a powerful modality fusion method. 相似文献
12.
《Information processing & management》2022,59(3):102931
Unsupervised feature selection is very attractive in many practical applications, as it needs no semantic labels during the learning process. However, the absence of semantic labels makes the unsupervised feature selection more challenging, as the method can be affected by the noise, redundancy, or missing in the originally extracted features. Currently, most methods either consider the influence of noise for sparse learning or think over the internal structure information of the data, leading to suboptimal results. To relieve these limitations and improve the effectiveness of unsupervised feature selection, we propose a novel method named Adaptive Dictionary and Structure Learning (ADSL) that conducts spectral learning and sparse dictionary learning in a unified framework. Specifically, we adaptively update the dictionary based on sparse dictionary learning. And, we also introduce the spectral learning method of adaptive updating affinity matrix. While removing redundant features, the intrinsic structure of the original data can be retained. In addition, we adopt matrix completion in our framework to make it competent for fixing the missing data problem. We validate the effectiveness of our method on several public datasets. Experimental results show that our model not only outperforms some state-of-the-art methods on complete datasets but also achieves satisfying results on incomplete datasets. 相似文献
13.
【目的/意义】针对当前利用计算机管理图像资源存在图像语义特征表达不足等问题,探索和分析了特征及
特征融合对分类结果的影响,提出了一种提高图像语义分类准确率的方法。【方法/过程】本文定义了四种图像风
格,将图像描述特征划分为三个层次,探究特征融合的特点,寻求能有效表达图像语义的特征。分别采用SVM、
CNN、LSTM 及迁移学习方法实现图像风格分类,并将算法组合以提高分类效果。【结果/结论】基于迁移学习的
ResNet18模型提取的深层特征能够较好地表达图像的高级语义,将其与SVM结合能提高分类准确率。特征之间
并不总是互补,在特征选择时应避免特征冗余,造成分类效率下降。【创新/局限】本文定义的风格数目较少,且图像
展示出的风格并不绝对,往往可以被赋予多种标签,今后应进一步丰富图像数据集并尝试进行多标签分类。 相似文献
14.
As access to information becomes more intensive in society, a great deal of that information is becoming available through diverse channels. Accordingly, users require effective methods for accessing this information. Conversational agents can act as effective and familiar user interfaces. Although conversational agents can analyze the queries of users based on a static process, they cannot manage expressions that are more complex. In this paper, we propose a system that uses semantic Bayesian networks to infer the intentions of the user based on Bayesian networks and their semantic information. Since conversation often contains ambiguous expressions, the managing of context and uncertainty is necessary to support flexible conversational agents. The proposed method uses mixed-initiative interaction (MII) to obtain missing information and clarify spurious concepts in order to understand the intention of users correctly. We applied this to an information retrieval service for websites to verify the usefulness of the proposed method. 相似文献
15.
[目的/意义]针对单纯使用统计自然语言处理技术对社交网络上产生的短文本数据进行意向分类时存在的特征稀疏、语义模糊和标记数据不足等问题，提出了一种融合心理语言学信息的Co-training意图分类方法。[方法/过程]首先，为丰富语义信息，在提取文本特征的同时融合带有情感倾向的心理语言学线索对特征维度进行扩展。其次，针对标记数据有限的问题，在模型训练阶段使用半监督集成法对两种机器学习分类方法（基于事件内容表达分类器与情感事件表达分类器）进行协同训练（Co-training）。最后，采用置信度乘积的投票制进行分类。[结论/结果]实验结果表明融入心理语言学信息的语料再经过协同训练的分类效果更优。 相似文献
16.
《Information processing & management》2023,60(4):103363
Government document analysis can help organizations to understand key policy points and make right response. To realize intelligent analysis of a volume of policies, we propose a discourse parsing technique for in-depth understanding of Chinese government documents (CGDs). Based on Superstructure Schema and Rhetorical Structure Theory (RST), we characterize the stylistic features and macrostructure patterns of CGDs and develop a discourse analysis framework to specify its functional structure and semantic system. A tree schema is adopted to portray the hierarchy of textual fragments in full text and formalize their representations in machine-based parsing, then a multi-head partition self-attention model is constructed to evaluate the discourse analysis framework. Experiment results show that our parsing model embedding with inherent CGD discourse features performs better than baselines. The highest f1-score in span and label prediction tasks researches 0.9209. The parsing model can be migrated to other discourse parsing tasks by considering specific genre features of different documents. 相似文献
17.
针对图书、期刊论文等数字文献文本特征较少而导致特征向量语义表达不够准确、分类效果差的问题,本文提出一种基于特征语义扩展的数字文献分类方法。该方法首先利用TF-IDF方法获取对数字文献文本表示能力较强、具有较高TF-IDF值的核心特征词;其次分别借助知网(Hownet)语义词典以及开放知识库维基百科(Wikipedia)对核心特征词集进行语义概念的扩展,以构建维度较低、语义丰富的概念向量空间;最后采用MaxEnt、SVM等多种算法构造分类器实现对数字文献的自动分类。实验结果表明:相比传统基于特征选择的短文本分类方法,该方法能有效地实现对短文本特征的语义扩展,提高数字文献分类的分类性能。 相似文献
18.
Extracting semantic relationships between entities from text documents is challenging in information extraction and important for deep information processing and management. This paper proposes to use the convolution kernel over parse trees together with support vector machines to model syntactic structured information for relation extraction. Compared with linear kernels, tree kernels can effectively explore implicitly huge syntactic structured features embedded in a parse tree. Our study reveals that the syntactic structured features embedded in a parse tree are very effective in relation extraction and can be well captured by the convolution tree kernel. Evaluation on the ACE benchmark corpora shows that using the convolution tree kernel only can achieve comparable performance with previous best-reported feature-based methods. It also shows that our method significantly outperforms previous two dependency tree kernels for relation extraction. Moreover, this paper proposes a composite kernel for relation extraction by combining the convolution tree kernel with a simple linear kernel. Our study reveals that the composite kernel can effectively capture both flat and structured features without extensive feature engineering, and easily scale to include more features. Evaluation on the ACE benchmark corpora shows that the composite kernel outperforms previous best-reported methods in relation extraction. 相似文献
19.
《Journal of The Franklin Institute》2023,360(9):6585-6608
Accurate position and attitude information is an important basis for normal driving of intelligent vehicles. In this paper, we investigate the estimation of position and attitude states for intelligent vehicles with low cost scheme. The low cost GNSS, camera, and proprioceptive sensors equipped by mass-produced vehicle are fused to estimate the states. The visual measurements adopted in this paper are based on the lateral distance and deflection angle to road features such as lane lines or curbs, which are generated more frequently than some other semantic features such as traffic lights, and leads to broader application scenario. Moreover, it is easier to implement compared with geometrical feature matching methods, since it only needs a simple prior map while latter needs large maps containing many high precision features. The visual measurements is often with large time delay due to negligible processing time. In order to fuse delayed measurements, a state-augmentation technique is adopted for the estimator design. The performance of the proposed method is evaluated by professional simulation software CarMaker, and shows that the incorporation of road features based visual measurement can effectively improve the position and attitude estimation accuracy by reducing the lateral position and yaw angle estimation error. 相似文献