Context- and Sentiment-Aware Networks for Emotion Recognition in Conversation

Tu, Geng; Wen, Jintao; Liu, Cheng; Jiang, Dazhi; Cambria, Erik

doi:10.1109/tai.2022.3149234

Cited by 57 publications

(17 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e purpose of this study is to make computers play the role of teachers and endue them with intelligent behaviors to replace teachers to become learners' guides and helpers to a certain extent, so as to achieve individualized teaching and individualized teaching effect. e intelligent teaching system in the user interface, teaching content and teaching process, and other aspects of a more comprehensive design mainly reflects the detailed description of the course, teaching course learning and learning process evaluation and other functions and at the same time, in the multimedia, teaching a set of speech synthesis, image display technology, with good man-machine interaction dialogue function [16,17].…”

Section: Related Workmentioning

confidence: 99%

Evaluation Method and Implementation of Vocal Music Teaching Performance under a Wireless Communication Environment

Liu

2022

Security and Communication Networks

View full text Add to dashboard Cite

With the development of society, modern educational technology and electronic information technology are more and more closely combined. Auxiliary teaching products based on computer technology, multimedia technology, and network technology emerge one after another. How to combine modern wireless communication technology with modern educational technology to evaluate the teaching effect has become one of the hot topics in the field of modern teaching research. In view of the lack of communication between teachers and students and evaluation methods of the teaching effect in traditional vocal music teaching, this paper designs a method of evaluation of vocal music teaching effect in a wireless communication environment. First, this paper designs a feedback system of vocal music teaching based on wireless communication. Second, due to the influence of vocal music teaching effect, the factors are diverse, and the neural network has the advantages in processing the data with nonlinear strong robustness and dynamic characteristics. And we use BP (back propagation) neural network as a mathematical model to receive teaching feedback information. Then, the simulation results show that the proposed method can not only evaluate the effect of vocal music teaching but also has good feasibility and practicability. Finally, the method proposed in this paper can help improve the teaching level and efficiency of the school and has a great theoretical value and practical potential.

show abstract

Section: Related Workmentioning

confidence: 99%

Evaluation Method and Implementation of Vocal Music Teaching Performance under a Wireless Communication Environment

Liu

2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…It has gained significant popularity due to numerous applications. Existing literature suggests that a wide range of deep learning methods have been applied to address the Emotion Recognition in Conversation (ERC) task [25], [26], [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37]. ICON [25] used a memory network architecture to model the interaction between self and inter-speaker states in two-party conversations.…”

Section: Related Workmentioning

confidence: 99%

Emotion Flip Reasoning in Multiparty Conversations

Kumar

Dudeja

Akhtar

et al. 2024

IEEE Trans. Artif. Intell.

View full text Add to dashboard Cite

In a conversational dialogue, speakers may have different emotional states and their dynamics play an important role in understanding dialogue's emotional discourse. However, simply detecting emotions is not sufficient to entirely comprehend the speaker-specific changes in emotion that occur during a conversation. To understand the emotional dynamics of speakers in an efficient manner, it is imperative to identify the rationale or instigator behind any changes or flips in emotion expressed by the speaker. In this paper, we explore the task called Instigator based Emotion Flip Reasoning (EFR), which aims to identify the instigator behind a speaker's emotion flip within a conversation. For example, an emotion flip from joy to anger could be caused by an instigator like threat. To facilitate this task, we present MELD-I, a dataset that includes ground-truth EFR instigator labels, which are in line with emotional psychology. To evaluate the dataset, we propose a novel neural architecture called TGIF, which leverages Transformer encoders and stacked GRUs to capture the dialogue context, speaker dynamics, and emotion sequence in a conversation. Our evaluation demonstrates state-of-the-art performance (+4−12% increase in F1-socre) against five baselines used for the task. Further, we establish the generalizability of TGIF on an unseen dataset in a zero-shot setting. Additionally, we provide a detailed analysis of the competing models, highlighting the advantages and limitations of our neural architecture.Impact Statement-Emotions play a pivotal role in deciding the impact of a statement uttered. However, in a conversational setting, simply identifying the emotions of utterances in a dialogue is not enough to characterize the emotional dynamic of the speaker. To this end, the proposed task of emotion-flip reasoning is eminent. The proposed flip explanations via triggers and instigators can help scrutinise how a particular type of remark or expression affects the end listener. A response generation mechanism can use these triggers or instigators as feedback to steer a conversation so that the user feels chipper.

show abstract

“…This is the first GCN-based model for emotion recognition, and good results have been obtained. Tu et al [18] presented a context and emotion-aware framework, termed Sentic GAT, which tends to select common sense knowledge consistent with the context semantics and emotion of the target utterance. This approach has also achieved good results.…”

Section: Related Workmentioning

confidence: 99%

RBA-GCN: Relational Bilevel Aggregation Graph Convolutional Network for Emotion Recognition

Lin

Huang

et al. 2023

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Emotion recognition in conversation (ERC) has received increasing attention from researchers due to its wide range of applications. As conversation has a natural graph structure, numerous approaches used to model ERC based on graph convolutional networks (GCNs) have yielded significant results. However, the aggregation approach of traditional GCNs suffers from the node information redundancy problem, leading to node discriminant information loss. Additionally, single-layer GCNs lack the capacity to capture long-range contextual information from the graph. Furthermore, the majority of approaches are based on textual modality or stitching together different modalities, resulting in a weak ability to capture interactions between modalities. To address these problems, we present the relational bilevel aggregation graph convolutional network (RBA-GCN), which consists of three modules: the graph generation module (GGM), similarity-based cluster building module (SCBM) and bilevel aggregation module (BiAM). First, GGM constructs a novel graph to reduce the redundancy of target node information. Then, SCBM calculates the node similarity in the target node and its structural neighborhood, where noisy information with low similarity is filtered out to preserve the discriminant information of the node. Meanwhile, BiAM is a novel aggregation method that can preserve the information of nodes during the aggregation process. This module can construct the interaction between different modalities and capture longrange contextual information based on similarity clusters. On both the IEMOCAP and MELD datasets, the weighted average F1 score of RBA-GCN has a 2.17∼5.

show abstract

Context- and Sentiment-Aware Networks for Emotion Recognition in Conversation

Cited by 57 publications

References 44 publications

Evaluation Method and Implementation of Vocal Music Teaching Performance under a Wireless Communication Environment

Evaluation Method and Implementation of Vocal Music Teaching Performance under a Wireless Communication Environment

Emotion Flip Reasoning in Multiparty Conversations

RBA-GCN: Relational Bilevel Aggregation Graph Convolutional Network for Emotion Recognition

Contact Info

Product

Resources

About