Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Multi-attention Recurrent Network for Human Communication Comprehension
Authors: Amir Zadeh, Paul Pu Liang, Soujanya Poria, Prateek Vij, Erik Cambria, Louis-Philippe Morency
AAAI 2018 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We perform extensive comparisons on six publicly available datasets for multimodal sentiment analysis, speaker trait recognition and emotion recognition. MARN shows stateof-the-art results performance in all the datasets. |
| Researcher Affiliation | Academia | Amir Zadeh Carnegie Mellon University, USA EMAIL Paul Pu Liang Carnegie Mellon University, USA EMAIL Soujanya Poria NTU, Singapore EMAIL Prateek Vij NTU, Singapore EMAIL Erik Cambria NTU, Singapore EMAIL Louis-Philippe Morency Carnegie Mellon University, USA EMAIL |
| Pseudocode | Yes | Algorithm 1 Multi-attention Recurrent Network (MARN), Long-short Term Hybrid Memory (LSTHM) and Multiattention Block (MAB) Formulation |
| Open Source Code | Yes | The code, hyperparameters and instruction on data splits are publicly available at https://github.com/A2Zadeh/MARN. |
| Open Datasets | Yes | We perform extensive comparisons on six publicly available datasets for multimodal sentiment analysis, speaker trait recognition and emotion recognition.CMU-MOSI (Zadeh et al. 2016), ICT-MMMO (W ollmer et al. 2013), You Tube (Morency, Mihalcea, and Doshi 2011), MOUD (Perez-Rosas, Mihalcea, and Morency 2013b), POM (Park et al. 2014), IEMOCAP (Busso et al. 2008). |
| Dataset Splits | Yes | To ensure generalization of the model, all the datasets are split into train, validation and test sets that include no identical speakers between sets, i.e. all the speakers in the test set are different from the train and validation sets. All models are re-trained on the same train/validation/test splits. For CMU-MOSI: There are 1284 segments in the train set, 229 in the validation set and 686 in the test set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments (e.g., CPU, GPU models, or memory specifications). |
| Software Dependencies | No | The paper mentions several tools and datasets used (e.g., 'glove.840B.300d', 'Facet', 'COVAREP', 'P2FA') but does not specify software dependencies like programming languages or libraries with version numbers (e.g., Python 3.x, TensorFlow 2.x). |
| Experiment Setup | No | The paper mentions that 'K is treated as a hyperparamter' and that 'extensive grid search on the number of parameters' was performed, but it does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) used for the experiments. |