Learn to Select via Hierarchical Gate Mechanism for Aspect-Based Sentiment Analysis
Authors: Xiangying Ran, Yuanyuan Pan, Wei Sun, Chongjun Wang
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct extensive experiments on the Sem Eval 2014 and Twitter dataset, and results demonstrate that our model outperforms attention based state-of-the-art baselines. We conduct experiments on three open standard datasets. The main evaluation metrics are Accuracy and Macro-averaged F1-score. |
| Researcher Affiliation | Academia | National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China Department of Computer Science and Technology, Nanjing University, Nanjing, China |
| Pseudocode | No | The paper describes the model architecture and mathematical formulations, but it does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions that neural approaches are implemented in PyTorch, with a footnote linking to the PyTorch homepage, but it does not state that the code for their specific methodology is open-sourced or provide a link to a code repository. |
| Open Datasets | Yes | We conduct experiments on three open standard datasets. The restaurant and laptop dataset are from Sem Eval 2014 [Pontiki et al., 2014]. Twitter dataset is a collection of tweets, introduced by [Dong et al., 2014]. |
| Dataset Splits | Yes | Specifically, all hyperparameters are tuned on 20% randomly held-out training data and the hyper-parameter collection producing the highest accuracy score is used for testing. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running the experiments, such as GPU models, CPU types, or memory specifications. |
| Software Dependencies | No | The paper mentions 'Pytorch' and 'Stanford Parser' and 'GloVe vectors', but it does not provide specific version numbers for these software components. The PyTorch mention includes a link to its general homepage (pytorch.org) not a version specific one. |
| Experiment Setup | Yes | We first obtain the POS tag results from Stanford Parser [Manning et al., 2014] and we use pre-trained Glo Ve vectors [Pennington et al., 2014] to initialize the word embeddings, the dimension is 300 and the vocabulary size is 2.2M7. For out-of-vocabulary words, we randomly initialize their embeddings from the uniform distribution U ( 0.01, 0.01). The convolutional kernel size k and the number of feature map s here we adopt is 3 and 50. The hidden state size, postion and POS tag embedding dimensions, i.e., dh, dp, dt are set to 50. To ease overfitting, we apply dropout on the input word embeddings of the bidirectional GRU and the final sentence representation v with dropout rate 0.5. All weight matrices are initialized with the uniform distribution U ( 0.01, 0.01) and the biases are initialized as zeros. Adam [Kingma and Ba, 2014] is adopted as the optimizer here. The batch size is set to 25 and the learning rate is set to 0.001. Specifically, all hyperparameters are tuned on 20% randomly held-out training data and the hyper-parameter collection producing the highest accuracy score is used for testing. |