BiERU: Bidirectional Emotional Recurrent Unit for Conversational Sentiment Analysis

@article{Li2022BiERUBE,
  title={BiERU: Bidirectional Emotional Recurrent Unit for Conversational Sentiment Analysis},
  author={Wei Li and Wei Li and Wei Shao and Shaoxiong Ji and E. Cambria},
  journal={Neurocomputing},
  year={2022},
  volume={467},
  pages={73-82}
}

DialogueTRM: Exploring Multi-Modal Emotion Dynamics in Conversations

This work extends the concept of emotion dynamics to multi-modal settings and proposes a Dialogue Transformer for simultaneously modeling the intra- modal and inter-modAL emotion dynamics.

ECPEC: Emotion-Cause Pair Extraction in Conversations

A novel dataset ConvECPE is built and a specifically designed two-step framework for the new ECPEC task, which aims to extract pairs of emotional utterances and corresponding cause utterances in conversations.

A survey on XAI and natural language explanations

A New Approach for Vietnamese Aspect-Based Sentiment Analysis

An improved approach for the Vietnamese Smartphone Feedback Dataset (UIT-ViSFD), collected and annotated carefully in 2021, is presented by employing the pretrained PhoBERT model with a proper pre-processing method and can bypass the state-of-the-art methods related to the UIT- ViSFD corpus.

Deep Emotion Recognition in Textual Conversations: A Survey

The survey highlights the advantage of leveraging techniques to address unbalanced data, the exploration of mixed emotions and the benefits of incorporating annotation subjectivity in the learning phase.
...

References

SHOWING 1-10 OF 76 REFERENCES

Convolutional Neural Networks for Sentence Classification

The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification, and are proposed to allow for the use of both task-specific and static vectors.

COSMIC: COmmonSense knowledge for eMotion Identification in Conversations

This paper proposes COSMIC, a new framework that incorporates different elements of commonsense such as mental states, events, and causal relations, and build upon them to learn interactions between interlocutors participating in a conversation.

Utterance-level Dialogue Understanding: An Empirical Study

This paper explores and quantify the role of context for different aspects of a dialogue, namely emotion, intent, and dialogue act identification, using state-of-the-art dialog understanding methods as baselines and employs various perturbations to distort the context of a given utterance and study its impact on the different tasks and baselines.

ABCDM: An Attention-based Bidirectional CNN-RNN Deep Model for sentiment analysis

Commonsense Knowledge Enhanced Memory Network for Stance Classification

A novel model named commonsense knowledge enhanced memory network is proposed, which jointly represents textual and Commonsense knowledge representation of given target and text and can improve stance classification.

Knowledge Guided Capsule Attention Network for Aspect-Based Sentiment Analysis

The proposed knowledge guided capsule network (KGCapsAN) implements the routing method by attention mechanism, and the results show that the proposed method yields the state-of-the-art.

SenticNet 6: Ensemble Application of Symbolic and Subsymbolic AI for Sentiment Analysis

This work integrates logical reasoning within deep learning architectures to build a new version of SenticNet, a commonsense knowledge base for sentiment analysis, and applies it to the interesting problem of polarity detection from text.

SentiVec: Learning Sentiment-Context Vector via Kernel Optimization Function for Sentiment Analysis

SentiVec is a kernel optimization function system for sentiment word embedding, which is based on two phases, and the optimal sentiment vectors successfully extract the features in terms of semantic and sentiment information, which makes it outperform the baseline methods on word similarity, word analogy, and SA tasks.

Image Polarity Detection on Resource-Constrained Devices

A design strategy for convolutional neural networks that can support image-polarity detection on edge devices and the outcomes of experimental sessions confirm the approach suitability.
...