To read the full-text of this research, you can request a copy directly from the authors.
... Relationship extraction is an essential aspect of information extraction, aiming to discern the semantic relationship between pairs of entities presented in natural language text. These entities may be linked explicitly or implicitly (Gao and Liu, 2023). Relationship extraction is of paramount importance in diverse applications and its techniques have been widely applied in knowledge graphs, question-and-answer systems, information retrieval, intelligent customer service and various other fields (Zhu et al., 2023). ...
Background
Building a large-scale medical knowledge graphs needs to automatically extract the relations between entities from electronic medical records (EMRs) . The main challenges are the scarcity of available labeled corpus and the identification of complexity semantic relations in text of Chinese EMRs. A hybrid method based on semi-supervised learning is proposed to extract the medical entity relations from small-scale complex Chinese EMRs.
Methods
The semantic features of sentences are extracted by a residual network and the long dependent information is captured by bidirectional gated recurrent unit. Then the attention mechanism is used to assign weights for the extracted features respectively, and the output of two attention mechanisms is integrated for relation prediction. We adjusted the training process with manually annotated small-scale relational corpus and bootstrapping semi-supervised learning algorithm, and continuously expanded the datasets during the training process.
Results
We constructed a small corpus of Chinese EMRs relation extraction based on the EMR datasets released at the China Conference on Knowledge Graph and Semantic Computing. The experimental results show that the best F1-score of the proposed method on the overall relation categories reaches 89.78%, which is 13.07% higher than the baseline CNN.
Extracting medical entity relations from Traditional Chinese Medicine (TCM) related article is crucial to connect domain knowledge between TCM with modern medicine. Herb accounts for the majority of Traditional Chinese Medicine, so our work mainly focuses on herb. The problem would be effectively solved by extracting herb-related entity relations from PubMed literature. In order to realize the entity relation mining, we propose a novel deep-learning model with improved layers without manual feature engineering. We design a new segment attention mechanism based on Convolutional Neural Network, which enables extracting local semantic features through word embedding. Then we classify the relations by connecting different embedding features. We first test this method on the Chemical-Induced Disease task and the experiment show better result comparing to other state-of-the-art deep learning methods. Further, we apply this method to a herbal-related data set (Herbal-Disease and Herbal Chemistry, HD-HC) constructed from PubMed to explore entity relation classification. The experiment shows superior results than other baseline methods.
This book contains a selection of papers accepted for presentation and discussion at ROBOT 2015: Second Iberian Robotics Conference, held in Lisbon, Portugal, November 19th-21th, 2015. ROBOT 2015 is part of a series of conferences that are a joint organization of SPR – “Sociedade Portuguesa de Robótica/ Portuguese Society for Robotics”, SEIDROB – Sociedad Española para la Investigación y Desarrollo de la Robótica/ Spanish Society for Research and Development in Robotics and CEA-GTRob – Grupo Temático de Robótica/ Robotics Thematic Group. The conference organization had also the collaboration of several universities and research institutes, including: University of Minho, University of Porto, University of Lisbon, Polytechnic Institute of Porto, University of Aveiro, University of Zaragoza, University of Malaga, LIACC, INESC-TEC and LARSyS.
Robot 2015 was focussed on the Robotics scientific and technological activities in the Iberian Peninsula, although open to research and delegates from other countries. The conference featured 19 special sessions, plus a main/general robotics track. The special sessions were about: Agricultural Robotics and Field Automation; Autonomous Driving and Driver Assistance Systems; Communication Aware Robotics; Environmental Robotics; Social Robotics: Intelligent and Adaptable AAL Systems; Future Industrial Robotics Systems; Legged Locomotion Robots; Rehabilitation and Assistive Robotics; Robotic Applications in Art and Architecture; Surgical Robotics; Urban Robotics; Visual Perception for Autonomous Robots; Machine Learning in Robotics; Simulation and Competitions in Robotics; Educational Robotics; Visual Maps in Robotics; Control and Planning in Aerial Robotics, the XVI edition of the Workshop on Physical Agents and a Special Session on Technological Transfer and Innovation.
We present a new method that we call generalized discriminant analysis (GDA) to deal with nonlinear discriminant analysis using kernel function operator. The underlying theory is close to the support vector machines (SVM) insofar as the GDA method provides a mapping of the input vectors into high-dimensional feature space. In the transformed space, linear properties make it easy to extend and generalize the classical linear discriminant analysis (LDA) to nonlinear discriminant analysis. The formulation is expressed as an eigenvalue problem resolution. Using a different kernel, one can cover a wide class of nonlinearities. For both simulated data and alternate kernels, we give classification results, as well as the shape of the decision function. The results are confirmed using real data to perform seed classification.
There has been a huge gap between male and female students in the field of science, technology, engineering, and mathematics. Women have always been inadequately represented in the field of information technology and engineering, both in universities and in the labor market. To understand the gender gap, the study aims to investigate how intrapersonal and interpersonal levels affect student in making decisions. It also explores the significant factors when choosing their university majors. The factors were categorized as practicality, environmental factors, passion, and personal interest (PEPP). In this study, the responses gathered from the survey were interpreted using text mining and visualization to draw meaningful insights, and recognize noteworthy keywords. Text visualization can be represented using graphs, word trees, or text clouds, which provides a more efficient perceptual competence to a wider audience. There are diverse reasons for students to register in their chosen majors.
Multiple kernel learning (MKL), which combines a set of prespecified basic kernels to improve the clustering performance, has become an important research topic. Unfortunately, the current methods have the following defects in noisy circumstances. 1) Their clustering performance may be significantly reduced due to the noise in the kernel, which is caused by the lack of a reliable discriminant guideline for basic kernel combinations. 2) The noise from corrupted data or occlusion may destroy the block-diagonal structures of the affinity matrices they obtained, which will affect the clustering performance when using spectral clustering. In this work, to solve the above problems, we propose an automatic weighted multikernel learning-based robust subspace clustering (AWLKSC) algorithm. The model integrates multikernel learning strategies, the Correntropy-Induced Metric (CIM), low rank approximation technology and block diagonal constraints. In addition, an effective AM&GST algorithm, which is integrated by alternating minimization and generalized soft-thresholding, is developed to optimize the AWLKSC. Seven types of noise are considered in the experiments, and the experimental results illustrate that AWLKSC is more effective and robust than several up-to-date single kernel and multiple kernel clustering methods.
To achieve a more desirable fault diagnosis accuracy by applying multi-domain features of vibration signals, it is significative and challenging to refine the most representative and intrinsic feature components from the original high dimensional feature space. A novel dimensionality reduction method for fault diagnosis is proposed based on local Fisher discriminant analysis (LFDA) which takes both label information and local geometric structure of the high dimensional features into consideration. Multi-kernel trick is introduced into the LFDA to improve its performance in dealing with the nonlinearity of mapping high dimensional feature space into a lower one. To obtain an optimal diagnosis accuracy by the reduced features of low dimensionality, binary particle swarm optimization (BPSO) algorithm is utilized to search for the most appropriate parameters of kernels and K-nearest neighbor (kNN) recognition model. Samples with labels are used to train the optimal multi-kernel LFDA and kNN (OMKLFDA-kNN) fault diagnosis model to obtain the optimal transformation matrix. Consequently, the trained fault diagnosis model implements the recognition of machinery health condition with the most representative feature space of vibration signals. A bearing fault diagnosis experiment is conducted to verify the effectiveness of proposed diagnostic approach. Performance comparison with some other methods are investigated, and the improvement for fault diagnosis of the proposed method are confirmed in different aspects.
Named entity relations are a foundation of semantic networks and ontology, and are widely used in information retrieval and machine translation, as well as automatic question and answering systems. In named entity relationships, relationship feature selection and extraction are two key issues. Characteristics of Chinese long sentences with complicated sentence patterns and many entities, as well as the data sparse problem, bring challenges for Chinese entity relationship detection and extraction tasks. To deal with above problems, a novel method based on syntactic and semantic features is proposed. The feature of dependency relation composition is obtained through the combination of their respective dependency relations between two entities. And the verb feature with the nearest syntactic dependency is captured from dependency relation and POS (part of speech). The above features are incorporated into feature-based relationship detection and extraction using SVM. Evaluation on a real text corpus in tourist domain shows above two features from syntactic and semantic aspects can effectively improve the performance of entity relationship detection and extraction, and outperform previously best-reported systems in terms of precision, recall and F1 value. In addition, the verb feature with nearest syntactic dependency achieves high effectiveness for relationship detection and extraction, especially obtaining the most prominent contribution to the performance improvement of data sparse entity relationships, and significantly outperforms the state-of-the-art based on the verb feature.
Traditional methods for event causal relation extraction covered only part of the explicit causal relation in the text. A method for event causal relation extraction is presented based on Cascaded Conditional Random Fields. The method casts the problem of event causal relation extraction as the labeling of event sequence. The Cascaded (Dual-layer) Conditional Random Fields is employed to label the causal relation of event sequence. The first layer of the Cascaded Conditional Random Fields model is used to label the semantic role of causal relation of the events, and then the output of the first layer is passed to the second layer for labeling the boundaries of the event causal relation. Experimental results show that this method not only covers each class of explicit event causal relation in the text, but also achieves good performance and the F-Measure of the overall performance arrives at 85.3%.
An autonomous processing method of Chinese service instruction is investigated to make robot understand natural language. This method directly maps Chinese service instructions to sequences of executable actions. Firstly, the collected corpus of the service instruction expressed in Chinese is deeply studied, and the corresponding relationship between the key information and syntactical structure is presented. According to the grammar rules of phrase chunk, a probability model is used for key information extraction. In order to resolve the problem of task decomposition, a task decomposition template (TDT) is presented. Based on this, the service instruction is mapped to sequences of actions. At last, the simulation about autonomous Chinese instruction processing is performed, and the experimental results of every step are provided, with the average accuracies of 92.9% in chunk marking, 92.7% in information extraction, and 97.2% in instruction parsing, which validates the correctness and availability of the proposed method.
Relation extraction is a fundamental task in information extraction, which is to identify the semantic relationships between two entities in the text. In this paper, deep belief nets (DBN), which is a classifier of a combination of several unsupervised learning networks, named RBM (restricted Boltzmann machine) and a supervised learning network named BP (back-propagation), is presented to detect and classify the relationships among Chinese name entities. The RBM layers maintain as much information as possible when feature vectors are transferred to next layer. The BP layer is trained to classify the features generated by the last RBM layer. The experiments are conducted on the Automatic Content Extraction 2004 dataset. This paper proves that a character-based feature is more suitable for Chinese relation extraction than a word-based feature. In addition, the paper also performs a set of experiments to assess the Chinese relation extraction on different assumptions of an entity categorization feature. These experiments showed the comparison among models with correct entity types and imperfect entity type classified by DBN and without entity type. The results show that DBN is a successful approach in the high-dimensional-feature-space information extraction task. It outperforms state-of-the-art learning models such as SVM and back-propagation networks.
On account of limitations and shortcomings of traditional audio recognition model, audio recognition with low SNR is deeply searched in this paper. Considering the functions and features of audio recognition, the general steps of audio recognition are analyzed and the application of Simple Multiple Kernel Learning (SMKL) in audio recognition with low SNR is presented to improve the recognition rate and accuracy of audio. The experimental results show that SMKL has a higher accuracy in identifying audio under the circumstance of low SNR than that recognition rate of each time of SMKL algorithm is higher than that of SVM algorithm. SMKL can be well applied to circumstances of large-scale sample data, complex dimension and massive heterogeneous information. Accuracy of audio recognition of kernel parameters optimization with grid-search method is higher than that with the method of fixed kernel parameters, the accuracy can be up to 85.52%. What’s more, effectiveness of grid-search method when determining kernel parameters can be seen from classification results
The environment map plays an important role in robot service, so it should contain not only appearance information about the whole service environment, but also their profoundness. The key contribution of the paper is the presentation of a novel semantic map, namely, a holography map composed of robot, family persons, operable items, local environments, as well as locations and path sections for home service robot cognizing its surroundings and providing services. Inspired by the object-oriented approach, the holography map is divided into three hierarchies of item-room-home and in detail 13 classes of objects. The design and storage of the object-oriented holography map are described comprehensively, and construction of the map is introduced. The execution of robot service based on the object-oriented holography map is discussed briefly. Experiments on real service robot demonstrate that the object-oriented holography map is nearer to human thinking and applicable to indoor robot service tasks.