When an entity contains one or more entities, these particular entities are referred to as nested entities. The Layered BiLSTM-CRF model can use multiple BiLSTM layers to identify nested entities. However, as the number of layers increases, the number of labels that the model can learn decreases, and it may not even predict any entities, thereby causing the model to stop stacking. Furthermore, the model will be constrained by the one-way propagation of information from the lower layer to the higher layer. The incorrect entities extracted by the outer layer will affect the performance of the inner layer. We propose a novel neural network for nested named entity recognition (NER) that dynamically stacks flat NER layers to address these issues. Each flat NER layer captures contextual information based on a pretrained model with more robust feature extraction capabilities. The model parameters of a flat NER layer and its input are entirely independent. The input of each layer is all of the word representations generated by the input sequence through the embedding layer. The independent input ensures that different flat NER layers will not be interfered with by other flat NER layers during model training and testing to reduce error propagation. Experiments show that our model obtains F1 scores of 76.9%, 78.1%, and 78.0% on the ACE2004, ACE2005, and GENIA datasets, respectively.

The multi-station agricultural machinery scheduling process mainly involves two key stages: order allocation and path planning. Order allocation methods based solely on spatial distance cannot ensure the continuity of agricultural operations. Multi-objective evolutionary algorithms are sensitive to the initial population quality and local search strategies for path planning, where unreasonable initial solutions or improper local search strategies can affect the diversity of solutions. Therefore, we propose a spatiotemporal allocation algorithm that constructs a spatiotemporal distance function to describe the feasibility of continuous operations and evaluates the spatiotemporal proximity of operation points and stations for clustering allocation. In terms of path planning, we design a learnable multi-objective evolutionary algorithm (LMOEA). First, a hybrid initialization strategy is used to enhance the initial population quality; second, a Q-learning-based local search method is constructed to adaptively adjust the search strategy to reduce ineffective iterations; finally, a dynamically adjusted crowding distance mechanism is introduced to improve the distribution of the solution set. Experimental results show that the spatiotemporal allocation algorithm improves the average cost and satisfaction by 4.09% and 3.28% compared to the spatial method. Compared with INSGA-II, HTSMOGA, and NNITSA algorithms, the LMOEA can obtain solutions of higher quality and greater diversity.

In recent years, many scholars have chosen to use word lexicons to incorporate word information into a model based on character input to improve the performance of Chinese relation extraction (RE). For example, Li et al. proposed the MG-Lattice model in 2019 and achieved state-of-the-art (SOTA) results. However, MG-Lattice still has the problem of information loss due to its model structure, which affects the performance of Chinese RE. This paper proposes an adaptive method to include word information at the embedding layer using a word lexicon to merge all words that match each character into a character input-based model to solve the information loss problem of MG-Lattice. The method can be combined with other general neural system networks and has transferability. Experimental studies on two benchmark Chinese RE datasets show that our method achieves an inference speed up to 12.9 times faster than the SOTA model, along with a better performance. The experimental results also show that this method combined with the BERT pretrained model can effectively supplement the information obtained from the pretrained model, further improving the performance of Chinese RE.

Multimodal sentiment analysis aims to uncover human affective states by integrating data from multiple sensory sources. However, previous studies have focused on optimizing model architecture, neglecting the impact of objective function settings on model performance. Given this, this study introduces a new framework, DMMSA, which utilizes the intrinsic correlation of sentiment signals and enhances the model’s understanding of complex sentiments. DMMSA incorporates coarse-grained sentiment analysis to reduce task complexity. Meanwhile, it embeds a contrastive learning mechanism within the modality, which decomposes unimodal features into similar and dissimilar ones, thus allowing for the simultaneous consideration of both unimodal and multimodal emotions. We tested DMMSA on the CH-SIMS, MOSI, and MOEI datasets. When only changing the optimization objectives, DMMSA achieved accuracy gains of 3.2%, 1.57%, and 1.95% over the baseline in five-class and seven-class classification tasks. In regression tasks, DMMSA reduced the Mean Absolute Error (MAE) by 1.46%, 1.5%, and 2.8% compared to the baseline.

How do humans analyze the sentiments embedded in text? When attempting to analyze a text, humans construct a “scene” in their minds through imagination based on the text, generating a vague image. They then synthesize the text and the mental image to derive the final analysis result. However, current sentiment analysis models lack such imagination; they can only analyze based on existing information in the text, which limits their classification accuracy. To address this issue, we propose the SceEmoNet model. This model endows text classification models with imagination through Stable diffusion, enabling the model to generate corresponding visual scenes from input text, thus introducing a new modality of visual information. We then use the Contrastive Language-Image Pre-training (CLIP) model, a multimodal feature extraction model, to extract aligned features from different modalities, preventing significant feature differences caused by data heterogeneity. Finally, we fuse information from different modalities using late fusion to obtain the final classification result. Experiments on six datasets with different classification tasks show improvements of 9.57%, 3.87%, 3.63%, 3.14%, 0.77%, and 0.28%, respectively. Additionally, we set up experiments to deeply analyze the model’s advantages and limitations, providing a new technical path for follow-up research.