A Dual-Stream Recurrence-Attention Network With Global-Local Awareness for Emotion Recognition in Textual Dialog

2023-07-02 · Jiang Li, XiaoPing Wang, Zhigang Zeng

In real-world dialog systems, the ability to understand the user's emotions and interact anthropomorphically is of great significance. Emotion Recognition in Conversation (ERC) is one of the key ways to accomplish this goal and has attracted growing attention. How to model the context in a conversation is a central aspect and a major challenge of ERC tasks. Most existing approaches struggle to adequately incorporate both global and local contextual information, and their network structures are overly sophisticated. For this reason, we propose a simple and effective Dual-stream Recurrence-Attention Network (DualRAN), which is based on Recurrent Neural Network (RNN) and Multi-head ATtention network (MAT). DualRAN eschews the complex components of current methods and focuses on combining recurrence-based methods with attention-based ones. DualRAN is a dual-stream structure mainly consisting of local- and global-aware modules, modeling a conversation simultaneously from distinct perspectives. In addition, we develop two single-stream network variants for DualRAN, i.e., SingleRANv1 and SingleRANv2. According to the experimental findings, DualRAN boosts the weighted F1 scores by 1.43% and 0.64% on the IEMOCAP and MELD datasets, respectively, in comparison to the strongest baseline. On two other datasets (i.e., EmoryNLP and DailyDialog), our method also attains competitive results.

📄 PDF Abstract BibTeX arXiv:2307.00449

Code (0)

등록된 구현이 없습니다.

Tasks

Emotion Recognition Emotion Recognition in Conversation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Sparsified State-Space Models are Efficient Highway Networks

2025-05-27 · Woomin Song, Jihoon Tack, Sangwoo Mo, Seunghyuk Oh 외

State-space models (SSMs) offer a promising architecture for sequence modeling, providing an alternative to Transformers by replacing expensive self-attention with linear recurrences. In this paper, we propose a simple y…

Mamba State Space Models

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models

2024-02-29 · Soham De, Samuel L. Smith, Anushan Fernando, Aleksandar Botev 외

Recurrent neural networks (RNNs) have fast inference and scale efficiently on long sequences, but they are difficult to train and hard to scale. We propose Hawk, an RNN with gated linear recurrences, and Griffin, a hybri…

Language Modelling Mamba

Temporal Fusion Transformers for Streamflow Prediction: Value of Combining Attention with Recurrence

2023-05-21 · Sinan Rasiya Koya, Tirthankar Roy

Over the past few decades, the hydrology community has witnessed notable advancements in streamflow prediction, particularly with the introduction of cutting-edge machine-learning algorithms. Recurrent neural networks, e…

Prediction

DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting

2019-11-03 · CIKM ’19, November 3–7, 2019, Beijing, China 2019 11 · Siteng Huang Donglin Wang∗

Multivariate time series forecasting has attracted wide attention in areas, such as system, traffic, and finance. The difficulty of the task lies in that traditional methods fail to capture complicated nonlinear dependen…

Multivariate Time Series Forecasting Time Series Time Series Analysis Time Series Forecasting

HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction

2026-05-22 · Chong Cheng, Peilin Tao, Nanjie Yao, Guanzhi Ding 외 arxiv

Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods often suffer from drift, jitter, or collapse on long sequences. We trace th…

3D Reconstruction