MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation

Tu, Quan; Li, Yanran; Cui, Jianwei; Wang, Bin; Wen, Ji-Rong; Yan, Rui

doi:10.48550/arxiv.2203.13560

Cited by 3 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing emotional support dialogue systems commonly utilize deep learning for strategy selection. For instance, Tu et al [3] proposed a mixed strategy learning method grounded in deep learning principles. On the other hand, Peng et al [11] incorporated seeker emotional feedback information for dialogue strategy selection.…”

Section: Conversation Strategymentioning

confidence: 99%

“…For instance, Zhong et al [15] leveraged the ConceptNet [16] module to enhance response generation and emotional states. Quan et al [3] captured the seekers' mental state by incorporating a generative commonsense model COMET [17], interacting with various factors to generate emotional responses. Deng et al [18] enhanced the system through knowledge in the field of mental health.…”

Section: Emotional Response Generationmentioning

confidence: 99%

“…The existing research mainly focuses on two aspects: firstly, the accurate prediction of dialogue strategies to tailor responses accordingly. For instance, Tu et al [3] utilized a mixed strategy prediction method. Secondly, the enhancement of the model's comprehension of dialogue context, such as the work of Peng et al [4] who designed a hierarchical graph network to capture user intent.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

AdMISC: Advanced Multi-Task Learning and Feature-Fusion for Emotional Support Conversation

Jia,

He,

Zhang

et al. 2024

Electronics

View full text Add to dashboard Cite

The emotional support dialogue system is an emerging and challenging task in natural language processing to alleviate people’s emotional distress. Each utterance in the dialogue has features such as emotion, intent, and commonsense knowledge. Previous research has indicated subpar performance in strategy prediction accuracy and response generation quality due to overlooking certain underlying factors. To address these issues, we propose Advanced Multi-Task Learning and Feature-Fusion for Emotional Support Conversation (AdMISC), which extracts various potential factors influencing dialogue through neural networks, thereby improving the accuracy of strategy prediction and the quality of generated responses. Specifically, we extract features affecting dialogue through dynamic emotion extraction and commonsense enhancement and then model strategy prediction. Additionally, the model learns these features through attention networks to generate higher quality responses. Furthermore, we introduce a method for automatically averaging loss function weights to improve the model’s performance. Experimental results using the emotional support conversation dataset ESConv demonstrate that our proposed model outperforms baseline methods in both strategy label prediction accuracy and a range of automatic and human evaluation metrics.

show abstract

Section: Conversation Strategymentioning

confidence: 99%

Section: Emotional Response Generationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AdMISC: Advanced Multi-Task Learning and Feature-Fusion for Emotional Support Conversation

Jia,

He,

Zhang

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…In addition, the author also constructed a high-quality ESC dataset ESConv with rich annotations and demonstrated the role of the ESConv dataset in training more emotional support systems through related experiments. Tu et al [65] proposed a new emotional support method, MISC, which integrates COMET into emotional support conversations and uses an attention mechanism to learn from the obtained knowledge selectively, grasps the user's emotions and changes in emotional support dialogue.…”

Section: Mental Health Assessmentmentioning

confidence: 99%

Emotion Recognition in Conversations: A Survey Focusing on Context, Speaker Dependencies, and Fusion Methods

Fu,

Yuan,

Zhang

et al. 2023

Electronics

View full text Add to dashboard Cite

As a branch of sentiment analysis tasks, emotion recognition in conversation (ERC) aims to explore the hidden emotions of a speaker by analyzing the sentiments in utterance. In addition, emotion recognition in multimodal data from conversation includes the text of the utterance and its corresponding acoustic and visual data. By integrating features from various modalities, the emotion of utterance can be more accurately predicted. ERC research faces challenges in context construction, speaker dependency design, and multimodal heterogeneous feature fusion. Therefore, this review starts by defining the ERC task, developing the research work, and introducing the utilized datasets in detail. Simultaneously, we analyzed context modeling in conversations, speaker dependency, and methods for fusing multimodal information concerning existing research work for evaluation purposes. Finally, this review also explores the research, application challenges, and opportunities of ERC.

show abstract

“…In response generation evaluation, we compare our model with Blenderbot-Joint [13], MISC [14], GLHG [15], PAL [6] and SUP-PORTER [16]. Note that PAL has the same structure as our model PESS-GEN, except for the persona extractor.…”

Section: Setupmentioning

confidence: 99%

School Characteristics and School Violence

Han¹

2021

School Violence in South Korea

View full text Add to dashboard Cite

Providing emotional support through dialogue systems is becoming increasingly important in today's world, as it can support both mental health and social interactions in many conversation scenarios. Previous works have shown that using persona is effective for generating empathetic and supportive responses. They have often relied on pre-provided persona rather than inferring them during conversations. However, it is not always possible to obtain a user persona before the conversation begins. To address this challenge, we propose PESS (Persona Extraction through Semantic Similarity), a novel framework that can automatically infer informative and consistent persona from dialogues. We devise completeness loss and consistency loss based on semantic similarity scores. The completeness loss encourages the model to generate missing persona information, and the consistency loss guides the model to distinguish between consistent and inconsistent persona. Our experimental results demonstrate that high-quality persona information inferred by PESS is effective in generating emotionally supportive responses.

show abstract

MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversation

Cited by 3 publications

References 28 publications

AdMISC: Advanced Multi-Task Learning and Feature-Fusion for Emotional Support Conversation

AdMISC: Advanced Multi-Task Learning and Feature-Fusion for Emotional Support Conversation

Emotion Recognition in Conversations: A Survey Focusing on Context, Speaker Dependencies, and Fusion Methods

School Characteristics and School Violence

Contact Info

Product

Resources

About