Metaphor, as a common type of linguistic expression, helps people intuitively understand complex concepts in communication, writing, and cognition. Metaphor components, including source-domain words and target-domain words, are critical elements for metaphor identification and interpretation. This article focuses on metaphor components and proposes a metaphor components identification framework employing F eedback-enhanced F eature-driven I n- C ontext L earning (FF-ICL) based on the large language model (LLM). Specifically, in-context learning and feedback mechanisms inspired by human learning are integrated. Firstly, a machine feedback mechanism is designed to perform prior predictions on training samples, constructing a candidate demonstration pool enriched with prediction results and feedback information. Secondly, a multi-head graph attention network (GAT) is introduced to capture the linguistic and structural information embedded in metaphorical expressions, producing feature-rich representations and establishing a vector repository. Based on the repository, the framework retrieves demonstrations most relevant to the input query across different feature dimensions, incorporating in-context prompts to effectively fine-tune the LLM. Experiments and analyses on public datasets demonstrate the superiority of FF-ICL. Furthermore, the metaphor concept mapping experiment validates the crucial role of metaphor components in downstream computational metaphor tasks. Relevant data and codes are available at https://github.com/WXLJZ/FF-ICL .

The widespread application of multi-view graph data has facilitated the development of multi-view graph clustering. Effectively learning multi-view node representations is crucial for discovering inherent patterns in complex systems. However, most existing methods struggle to handle data with both multi-attribute and multi-relation simultaneously, while both attributes and relations are essential for graph clustering. Therefore, this paper proposes a dual-adaptive fusion multi-view clustering method based on graph autoencoder. It utilizes multi-view encoders and decoders to encode and reconstruct inputs separately. Additionally, a dual-adaptive fusion module is introduced to integrate multi-view node representations. Through consistency clustering, the proposed method explores the probability distribution consistency among different views, thereby achieving consistent clustering results. Experimental results on three datasets demonstrate the effectiveness of the proposed method in clustering tasks.

In action recognition tasks, voting fusion can be used to combine classification results from multiple modalities to improve recognition accuracy and robustness. This paper proposes a novel weighted voting fusion method for multi-modality-based action recognition, which includes a weight generation method and three fusion strategies based on these weights. For weight generation, action instances are first classified based on single modality to obtain prediction scores for each action class. An adaptive weight for each modality is then generated by assigning a higher value to the modality with better classification, which is used for balancing the modality contributions of different actions. In the fusion stage, three fusion strategies are proposed to apply the adaptive weights to obtain the final class label, including maximum fusion, elimination weighted voting and maximum weighted voting. Experiments conducted on three kinds of modality fusion demonstrate the effectiveness of the proposed method.

Emotion recognition in conversation is important for an empathetic dialogue system to understand the user’s emotion and then generate appropriate emotional responses. However, most previous researches focus on modeling conversational contexts primarily based on the textual modality or simply utilizing multimodal information through feature concatenation. In order to exploit multimodal information and contextual information more effectively, we propose a multimodal directed acyclic graph (MMDAG) network by injecting information flows inside modality and across modalities into the DAG architecture. Experiments on IEMOCAP and MELD show that our model outperforms other state-of-the-art models. Comparative studies validate the effectiveness of the proposed modality fusion method.

Since learning in Boltzmann machines is typically quite slow, there is a need to restrict connections within hidden layers. However, theresulting states of hidden units exhibit statistical dependencies. Based on this observation, we propose using l1/l2 regularization upon the activation probabilities of hidden units in restricted Boltzmann machines to capture the local dependencies among hidden units. This regularization not only encourages hidden units of many groups to be inactive given observed data but also makes hidden units within a group compete with each other for modeling observed data. Thus, the l1/l2 regularization on RBMs yields sparsity at both the group and the hidden unit levels. We call RBMs trained with the regularizer sparse group RBMs (SGRBMs). The proposed SGRBMs are appliedto model patches of natural images, handwritten digits and OCR English letters. Then to emphasize that SGRBMs can learn more discriminative features we applied SGRBMs to pretrain deep networks for classification tasks. Furthermore, we illustrate the regularizer can also be applied to deep Boltzmann machines, which lead to sparse group deep Boltzmann machines. When adapted to the MNIST data set, a two-layer sparse group Boltzmann machine achieves an error rate of 0.84%, which is, to our knowledge, the best published result on the permutation-invariant version of the MNIST task.