Lin Miao

Current knowledge graph reasoning methods actually use the same state representations and a fixed decision method to complete the total reasoning process. They are not able to truly use the different levels of attribute information. To overcome this problem, we propose a multi-level reinforcement learning reasoning model based on adaptive hierarchical feature fusion. Our model divides attribute information into coarse-grained attributes and fine-grained attributes. In this way, our model can better balance overall semantics and details, thereby holding connections between entities and relationships. We design an adaptive hierarchical feature fusion mechanism. Our model dynamically determines whether it pays more attention to attribute information or relationship according to the needs of the current task, rather than constantly using the same weights. This enables our model to have better performance in different reasoning situations. We improve the decision process of the model, making the model know which relationships to focus on and which are less relevant to skip, thereby reducing ineffective search. According to the results of the experiment, our method is superior to the existing reinforcement learning reasoning methods, including MINERVA, AdaPath, CURL, and HMR. Our model improves MRR, Hits@1, Hits@3, and Hits@10 indicators compared with these baseline models. This shows that our method can improve the accuracy of inference and verify the effectiveness of our model in complex knowledge graph inference tasks.

Extracting structured threat intelligence from unstructured cybersecurity texts requires accurate identification of entities together with their underlying semantic relations. However, threat reports often exhibit intricate sentence structures, long-range contextual dependencies, and tightly coupled entity–relation patterns, which pose substantial challenges for existing extraction approaches. To address these challenges, this study investigates joint entity–relation extraction from the perspective of semantic dependency modeling and develops HDIM-JER, a unified framework that captures structured interactions among heterogeneous linguistic features. HDIM-JER integrates character-level cues, contextual representations, and higher-order semantic dependency evidence to enhance structural awareness during joint inference, where different second-order dependency configurations provide an interpretable perspective on structurally symmetric and hierarchically asymmetric interaction patterns among entity–relation instances. By incorporating multi-level dependency interactions, HDIM-JER effectively alleviates error propagation associated with pipeline-based architectures and improves the modeling of complex relational dependencies. Extensive experiments on a threat intelligence corpus and a public benchmark dataset demonstrate consistent performance improvements over representative state-of-the-art methods in both entity recognition and relation extraction, confirming the effectiveness of higher-order semantic dependency interaction modeling for threat intelligence analysis.

Domain adaptation in image semantic segmentation has attracted more and more attention from computer vision and machine learning researchers. While the high cost of manual annotation is an unavoidable bottleneck in the semantic segmentation task, it is a high-quality solution to adopt pixel-level annotation from synthetic data, which provides additional support for deep learning training. Numerous studies have attempted to comprehensively investigate deep domain adaptation, but there is less focus on the sub-direction of the semantic segmentation task. This paper is devoted to this new topic in transfer learning. First, we describe the terminology and background concepts in this field. Next, the main datasets and evaluation metrics are introduced. Then, we classify the current research methods and introduce their contributions. Moreover, the quantitative results of the methods involved are compared, and the results are discussed. Finally, we suggest future research directions for this field. We believe researchers who are interested in this field will find this work to be an effective reference.

The technology of military equipment entity extraction, a crucial component in constructing military knowledge bases, holds significant research value and theoretical importance for guiding the development and improvement of equipment support forces. In the military domain, equipment entities exhibit a phenomenon of nesting, where one entity is contained within another, and abbreviations or codes are frequently used to represent these entities. To address this complexity, this paper proposes a method named CoTNER for extracting entities. Initially, a large-scale language model is used to perform data augmentation with chain-of-thought on the original dataset, providing additional semantic and contextual information. Subsequently, the augmented dataset is fine-tuned on a small-scale language model to adapt it to the task of military equipment entity extraction and to enhance its ability to learn complex rules specific to the domain of military equipment. Additionally, a high-quality data filtering strategy based on instruction-following difficulty scoring is proposed to address the catastrophic forgetting issue that may occur during the fine-tuning of large language models. The experimental results demonstrate that the proposed military equipment entity extraction method outperforms mainstream traditional deep learning methods, validating the effectiveness of CoTNER.

Knowledge graph completion is one of the steps of knowledge graph construction. It aims to complete the incomplete triple data in the initially constructed knowledge graph and make the data in the knowledge graph more abundant and complete. At present, there are few studies on knowledge graph completion in the equipment field, and the attribute and relationship samples in the equipment knowledge graph are prone to uneven distribution, while the traditional knowledge graph completion method is difficult to solve the problem of uneven distribution of attribute and relationship samples. Therefore, this paper proposes an internal instance type completion method of equipment knowledge graph based on EP2TP-TRT. First, the TransE model is used to embed the relationship and attributes of the equipment instance, respectively. Then, the EP2TP model is used to map the instance attributes, and the TRT model is used to map the type relationship. Finally, the scores of the EP2TP and TRT models are integrated by designing different weights, and the training prediction is carried out to enhance the representation ability of instance information and type information. Compared with the mainstream advanced models, this method improves the MRR and HITS @ 1 indicators by about 0.89% and 2.1%, respectively.

Aiming at the problem that the traditional extraction method caused by the diversification of weapon attributes has a large amount of work to construct the label of weapon attributes, in this paper, we propose a weapon attribute value extraction method based on bidirectional long-term and short-term memory network (Bi-LSTM) and attention mechanism. The method first uses the Bi-LSTM model to extract the features of the input text and attribute names. Then, the attention mechanism focuses on the relations between words and attributes in the sentence. Afterward, the global BIO tag marks the position of the attribute values in the sentence. In this way, the method can reduce the workload during the corpus preparation period to improve the generalization ability of the model so that it can extract different weapon attribute data. Compared with Bi-LSTM, Bi-LSTM_CRF, and OpenTag from the experimental results, the F1 values of the proposed model on the weapon domain attribute dataset are increased by about 6.9%, 5.7%, and 2.5%, respectively.

Early classification of time series data aims to classify a time series with high accuracy as early as possible. This paper provides a concise yet comprehensive overview of early classification techniques for time series data, specifically focusing on two widely adopted approaches: the multi-model approach and the shapelet-based approach. By examining the limitations associated with these approaches, this study introduces an innovative incremental approach as an alternative. The incremental approach exhibits the ability to learn and adapt the classification model to new data while retaining existing knowledge, without the need to build new models from scratch for each classification task. In the experiments with time series “occupancy detection” dataset, time series approach, shapelet approach and incremental approach have been implemented. The experimental results clearly demonstrate that the incremental approach outperforms the other methods in terms of both accuracy and earliness. However, it is important to note that the incremental approach exhibited a higher false positive rate, indicating the presence of misclassifications that warrant further investigation and refinement. This work shows that incremental approach is feasible and efficient for early classification of time series, but also shows room for improvement. Overall, this study contributes to the understanding of early classification techniques for time series data, paving the way for improved decision-making and analysis in various domains reliant on timely and accurate classification of time series data.