The task of event extraction contains subtasks including detections for entity mentions, event triggers and argument roles. Traditional methods solve them as a pipeline, which does not make use of task correlation for their mutual benefits. There have been recent efforts towards building a joint model for all tasks. However, due to technical challenges, there has not been work predicting the joint output structure as a single task. We build a first model to this end using a neural transition-based framework, incrementally predicting complex joint structures in a state-transition process. Results on standard benchmarks show the benefits of the joint model, which gives the best result in the literature.

Evaluating the susceptibility of regional landslides is one of the core steps in spatial landslide prediction. Starting from multiresolution image segmentation and object-oriented classification theory, this paper uses the four parameters of entropy, energy, correlation, and contrast from remote-sensing images in the Zigui–Badong section of Three Gorges Reservoir as image texture factors; the original image data for the study area were divided into 2279 objects after segmentation. According to the various indicators of the existing historical landslide database in the Three Gorges Reservoir area, combined with the classification processing steps for different types of multistructured data, the relevant geological evaluation factors, including the slope gradient, slope structure, and engineering rock group, were rated based on expert experience. From the perspective of the object-oriented segmentation of multiresolution images and geological factor rating classification, the C5.0 decision tree susceptibility classification model was constructed for the prediction of four types of landslide susceptibility units in the Zigui–Badong section. The mapping results show that the engineering rock group of a high-susceptibility unit usually develops in soft rock or soft–hard interphase rock groups, and the slope is between 15°–30°. The model results show that the average accuracy is 91.64%, and the kappa coefficients are 0.84 and 0.51, indicating that the C5.0 decision tree algorithm provides good accuracy and can clearly divide landslide susceptibility levels for a specific area, respectively. This landslide susceptibility classification, based on multiresolution image segmentation and geological factor classification, has potential applicability.

Integrating Unmanned Aerial Vehicles (UAVs) into military operations has become increasingly significant in recent years. In practical missions, UAVs are usually operated in unpredictable conditions, requiring robust planning to adapt to real-time changes. Thus, an effective path-planning algorithm is essential for navigating UAVs through complex terrains. However, the commonly used Rapidly-exploring Random Tree (RRT) algorithm for UAV path planning often generates suboptimal paths that require extensive post-processing to improve. While its variants can converge to the optimal solution, they suffer from more memory and computation consumption. On the other hand, purely learning-based methods could result in planning failures or excessively long paths generated for obstacle avoidance. In this work, we introduce a UAV path planning model that integrates diverse sensor data through a neural network architecture featuring CNN, LSTM, and an attention mechanism. Then, the deep learning-enhanced RRT algorithm combines the neural module with the informed sampling methods for adaptive and efficient pathfinding in dynamic environments. After carefully considering the trade-offs among path optimality, computational efficiency, and fewer turning angles, our approach exhibits superior overall performance compared to Informed RRT*, Batch Informed Trees (BIT*) algorithms, and the state-of-the-art Layered RQN.