相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Jiawen Deng et al.
Summary: This article systematically surveys the latest advancements in textual emotion recognition using deep neural networks. It discusses the remaining challenges and opportunities in this field, including the lack of large-scale and high-quality datasets, fuzzy emotional boundaries, incomplete emotional information extraction from texts, and emotion recognition in dialogues. The article provides necessary knowledge and new insights for researchers to better understand the current state, challenges, and future directions in this field.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Bin Liang et al.
Summary: The state-of-the-art approaches to targeted aspect-based sentiment analysis (TABSA) are mostly built on deep neural networks with attention mechanisms. One problem is that embeddings of targets and aspects are either pre-trained from large external corpora or randomly initialized. We propose an embedding refinement framework called RAEC (Refining Affective Embedding from Context) that incorporates affective commonsense knowledge and word relative location information to derive context-affective embeddings. Experimental results show that our framework achieves state-of-the-art results compared to models relying on pre-trained word embeddings or built on other embedding refinement methods.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Geng Tu et al.
Summary: Both discrete and dimensional models can be applied to emotion recognition tasks, and in this work, a mechanism combining the advantages of these two models is introduced. The multitask graph neural network (MGNN) is proposed to implement this mechanism, balancing exploration and exploitation through a weighting scheme and self-attention mechanism. Experimental results show the superiority of MGNN over advanced methods on tested datasets.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Bin Liang et al.
Summary: This paper proposes a graph convolutional network model Sentic GCN based on SenticNet to enhance the affective dependencies of sentences for aspect-based sentiment analysis. By integrating emotional knowledge from SenticNet, the model effectively handles contextual affective information in sentences, improving the effectiveness of sentiment polarity detection towards specific aspects.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Wei Li et al.
Summary: This paper presents a fast, compact, and parameter-efficient framework for conversational sentiment analysis, which outperforms the state of the art in most cases according to extensive experiments on three standard datasets.
Article
Engineering, Electrical & Electronic
Ke Zhang et al.
Summary: The ERLDK model proposed in this paper uses reinforcement learning and domain knowledge for multimodal emotion recognition in conversational videos, providing real-time capability. The model utilizes history utterances as emotion-pairs to recognize the context of the subsequent utterance. Experimental results demonstrate that ERLDK achieves state-of-the-art performance on weighted average and most specific emotion categories.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Weizhi Nie et al.
Summary: Sentiment analysis and emotion detection in conversation have attracted increasing attention in the fields of social robot, social network, and intelligent voice assistant. In this paper, an incremental graph convolution network (I-GCN) is proposed to handle emotion detection in conversation. The graph structure is utilized to represent the semantic correlation information of utterances, while the incremental graph structure is used to preserve the temporal change information. Two types of GCN, namely utterance-level GCN (U-GCN) and speaker-level GCN (S-GCN), are introduced to learn the features of utterances. The parameters of the model are fine-tuned with new utterances to enhance the contribution of temporal change information. Experimental results show the effectiveness of the proposed method in three conversation corpuses.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Proceedings Paper
Acoustics
Yunhe Xie et al.
Summary: The recent surge in open conversational data has led to increased attention on Emotion Recognition in Spoken Dialog (ERSD). However, the limited scale of existing ERSD datasets restricts the model's reasoning capabilities. This paper proposes a Commonsense Knowledge Enhanced Network with a retrospective loss (CKE-Net) to hierarchically perform dialog modeling, knowledge integration, and historical state retrospect. Experimental results show that the designed modules consistently improve performance, and the CKE-Net outperforms state-of-the-art models on benchmark datasets.
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2022)
Article
Computer Science, Information Systems
Minjie Ren et al.
Summary: This paper introduces a novel approach named LR-GCN for Emotion Recognition in Conversation (ERC). By leveraging speaker dependency and latent correlations among utterances, LR-GCN achieves better performance compared to existing state-of-the-art methods.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Computer Science, Artificial Intelligence
Songlong Xing et al.
Summary: This article proposes an Adapted Dynamic Memory Network (A-DMN) for Emotion Recognition in Conversation (ERC), which effectively synthesizes self and inter-speaker influences and obtains refined representations through multiple iterations. Additionally, the study explores cross-modal fusion in multimodal ERC and presents a convolution-based method that is efficient in extracting local interactions.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Dayu Li et al.
Summary: This paper investigates emotion inference in conversations by leveraging external inferential knowledge to enhance the effectiveness of emotion inference. The proposed conversation modeling module and knowledge integration strategy successfully optimize emotion inference in conversations, demonstrating the benefits of leveraging commonsense knowledge.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Zheng Lian et al.
Summary: The paper proposes a Dialogical Emotion Correction Network (DECN) to improve the emotion recognition performance in conversations, utilizing a graphical network and a multi-head attention based bi-directional GRU component. Experimental results show that DECN can enhance the performance of emotion recognition strategies with few parameters and low computational complexity.
Article
Computer Science, Artificial Intelligence
Vaibhav Bhat et al.
Summary: Emotion recognition in conversations is crucial for various virtual chatbots, but current models face issues such as loss of contextual information and inability to pass on emotional information. The proposed AdCOFE model addresses these issues by utilizing knowledge graphs, sentiment lexicons, and natural language phrases for feature extraction, showing benefits in capturing emotions according to experiments on conversation datasets.
PEERJ COMPUTER SCIENCE
(2021)
Article
Computer Science, Information Systems
Guorong Xiao et al.
Summary: This paper introduces a multimodality sentiment analysis approach for sentiment recognition in the social Internet of Things, achieving significant improvement in model performance through contextual information fusion and branch memory networks.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Haozhe Liu et al.
Summary: The study focuses on conversational emotion recognition and proposes a new framework TANTP, which effectively captures the emotional semantic features of utterances and achieves superior performance in experiments.
ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2021, PT II
(2021)
Article
Acoustics
Zheng Lian et al.
Summary: The study proposes a multimodal learning framework for conversational emotion recognition, named conversational transformer network (CTNet). By modeling intra-modal and cross-modal interactions, capturing temporal information using lexical and acoustic features, and utilizing a bi-directional GRU component and speaker embeddings to model context-sensitive and speaker-sensitive dependencies, the experimental results demonstrate the effectiveness of the method. The approach shows a performance improvement of 2.1% to 6.2% on weighted average F1 over state-of-the-art strategies.
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Yukun Ma et al.
INFORMATION FUSION
(2020)
Article
Psychology, Multidisciplinary
James J. Gross et al.
Article
Computer Science, Artificial Intelligence
Franco Scarselli et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS
(2009)
Article
Computer Science, Interdisciplinary Applications
Carlos Busso et al.
LANGUAGE RESOURCES AND EVALUATION
(2008)
