With the increasing use of interactive applications, the importance of Emotion recognition in conversation (ERC) is growing. Current research in the ERC domain mainly emphasizes the extraction of contextual information. However, challenges arise due to multi-turn conversation scenarios and the natural transformation of emotions, particularly in identifying subtle emotion transfers. Moreover, emotions exhibit nonlinear characteristics in semantic spaces, leading to potential confusion when discerning similar semantic emotions in the Euclidean semantic space. To address these issues, this study proposes a Poincaré-based dual-strategy emotion tracker for emotion recognition in conversation (PeTracker), which introduces the hyperbolic space representation in the ERC domain. Based on the spatial properties of the hyperbolic space representation to capture the nonlinear relationships among features, PeTracker encompasses two learning strategies. Poincaré emotional geometry curriculum learning (PGCL) and Poincaré emotional stratification contrastive learning (PSCL). In PGCL, the similarity of emotion labels is effectively discerned using the Poincaré distance, quantifying emotion transfer distances and facilitating the identification of subtle emotion transfers in utterance. In PSCL, PeTracker extracts and adapts multi-level features, mapping them to the Poincaré ball space to build emotion prototype-based contrastive learning. This process enhances the model’s ability to distinguish between similar emotion labels. while alleviating potential label confusion issues. Experimental results on three general datasets demonstrate that PeTracker achieves optimal or near-optimal performance. Furthermore, the study investigates the role and impact of the Poincaré ball in differentiating similar emotions.

The rapid development of wireless communications has driven the need for careful optimization of network parameters to improve network performance and reduce operational cost. Traditional methods, however, struggle with the vast number of tunable parameters and lack scalability in diverse network scenarios. To address these challenges, this paper introduces an optimization-inspired bipartite graph neural network (Bi-GNN) approach for scalable network optimization. Our approach leverages the bipartite structure of network topologies, and incorporates a message-passing mechanism by unfolding the Zeroth-Order Block Coordinate Projected Gradient Descent (ZO-BCPGD) algorithm, which ensures not only high-performance optimization but also manageable computational demand. We demonstrate the permutation and dimensionality equivariance property of the Bi-GNN, which significantly enhances the model’s generalizability across various network structures and sizes. Furthermore, we theoretically analyze the expressive power and generalization ability of the Bi-GNN, demonstrating its adeptness at complex network optimization tasks. The training process, parallel execution, and practical implementation techniques are also discussed to ensure the model’s applicability in real-world scenarios. Numerical results verify that the Bi-GNN outperforms existing methods in both coverage ratios and computational cost. Furthermore, our approach exhibits robust scalability across various network scenarios, making it a versatile tool for optimizing a wide range of wireless networks.

Current supervised word sense disambiguation models have obtained high disambiguation results using annotated information of different word senses and pre-trained language models. However, the semantic data of the supervised word sense disambiguation models are in the form of short texts, and much of the corpus information is not rich enough to distinguish the semantics in different scenarios. This article proposes a bi-encoder word sense disambiguation method combining a knowledge graph and text hierarchy structure, by introducing structured knowledge from the knowledge graph to supplement more extended semantic information, using the hierarchy of contextual input text to describe the meaning of words and phrases, and constructing a BERT-based bi-encoder, introducing a graph attention network to reduce the noise information in the contextual input text, so as to improve the disambiguation accuracy of the target words in phrase form and ultimately improve the disambiguation effectiveness of the method. By comparing the method with the latest nine comparison algorithms in five test datasets, the disambiguation accuracy of the method mostly outperformed the comparison algorithms and achieved better results.

In recent years, emotion recognition in conversations has gained widespread attention due to its extensive applications. Many recent studies have focused on perceiving conversational context from the perspective of capturing dialogue clues. However, these studies often use the entire conversation sequence to represent the dialogue clues, which may result in insufficient representation of the speaker's emotional dynamics in multi-turn conversation. To address these issues, we propose a novel dual-channel dialogue clues embedding context perception network (Dialogue-Clues) that integrates dialogue clues information into global conversation context modeling. We also introduce a dual-channel dialogue clues perception architecture that captures and reinforces both static and dynamic dialogue clues in conversations, and bidirectionally reinforces both types of dialogue clues information. To better represent dynamic dialogue clues, we construct a novel speaker-interaction isomorphic graph structure for the dual-channel dialogue clues perception architecture. Through extensive comparisons with ten existing methods on four public datasets, we confirm the effectiveness of the proposed method. The results demonstrate that integrating Dialogue-Clues information can improve the ability of context modeling.

Aspect-based sentiment classification aims to automatically predict the sentiment polarity of the specific aspect in a text. However, it is challenging to confirm the mapping between the aspect and the core context since a number of existing methods concentrate on building the global relations of the full context rather than the partial connections based on the aspects. Motivated by the fundamental insights of reinforcement learning, we propose a novelHeterogeneousReinforcementLearningNetwork for aspect-based sentiment analysis (HRLN) to alleviate these issues, which contains two primary components, a heterogeneous network module, and a knowledge graph-based reinforcement learning module consistent with common-sense knowledge and emotional knowledge. To evaluate the effectiveness of HRLN, we conduct extensive experiments on five benchmark datasets, which indicate that HRLN achieves competitive performance and yields state-of-the-art results on all datasets. Additionally, we present an intuitive comprehension of why our HRLN model is more robust for aspect-based sentiment classification via case studies.