Speaker-Guided Encoder-Decoder Framework for Emotion Recognition in Conversation
Authors: Yinan Bao, Qianwen Ma, Lingwei Wei, Wei Zhou, Songlin Hu
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results demonstrate the superiority and effectiveness of SGED. |
| Researcher Affiliation | Academia | Yinan Bao1,2 , Qianwen Ma1,2 , Lingwei Wei1,2 , Wei Zhou1, and Songlin Hu1,2 1Institute of Information Engineering, Chinese Academy of Sciences 2School of Cyber Security, University of Chinese Academy of Sciences {baoyinan, maqianwen, weilingwei, zhouwei, husonglin}@iie.ac.cn |
| Pseudocode | No | The paper describes the model architecture and processes using mathematical formulas and descriptive text, but it does not include a dedicated pseudocode or algorithm block. |
| Open Source Code | No | The paper does not provide a direct link or explicit statement about the availability of its source code. |
| Open Datasets | Yes | We evaluate our proposed framework on three ERC benchmark datasets. IEMOCAP. A two-party conversation dataset for ERC [Busso et al., 2008]... MELD. A multi-party conversation dataset collected from the TV series Friends [Poria et al., 2019a]... Emory NLP. A multi-party conversation dateset collected from Friends, but varies from MELD in the choice of scenes and emotion labels [Zahiri and Choi, 2018]. |
| Dataset Splits | Yes | Dataset Conversations Utterances Train Val Test Train Val Test IEMOCAP 120 31 5810 1623 MELD 1038 114 280 9989 1109 2610 Emory NLP 713 99 85 9934 1344 1328... Since this dataset has no validation set, we follow [Shen et al., 2021b] to use the last 20 conversations in the training set for validation. |
| Hardware Specification | No | The paper does not specify the hardware used for the experiments (e.g., GPU models, CPU, memory). |
| Software Dependencies | No | The paper mentions using Adam as the optimizer and fine-tuned RoBERTa features, but it does not specify version numbers for any software dependencies like Python, PyTorch, TensorFlow, or CUDA. |
| Experiment Setup | Yes | The learning rate and batch size are selected from {1e-5, 5e-5, 1e-4, 5e-4} and {8, 16, 32}, respectively. The dimension of hidden vector h is set to 300 and the dimension of label embedding is set to 100. The feature size for the RoBERTa extractor is 1,024. We use the fine-tuned RoBERTa features provided by Shen et al., [2021b]. Each training process contains 60 epochs. |