Interactive Attention Networks for Aspect-Level Sentiment Classification
Authors: Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on Sem Eval 2014 Datasets demonstrate the effectiveness of our model. |
| Researcher Affiliation | Academia | Dehong Ma1, Sujian Li1, Xiaodong Zhang1, Houfeng Wang1,2 1MOE Key Lab of Computational Linguistics, Peking University, Beijing, 100871, China 2Collaborative Innovation Center for Language Ability, Xuzhou, Jiangsu, 221009, China {madehong, lisujian, zxdcs, wanghf}@pku.edu.cn |
| Pseudocode | No | The paper presents the overall architecture in Figure 1 and mathematical equations for the model components, but it does not include structured pseudocode or an algorithm block. |
| Open Source Code | No | The paper does not provide any explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | We conduct experiments on Sem Eval 2014 Task 41 to validate the effectiveness of our model. The Sem Eval 2014 dataset is composed of reviews in two categories: Restaurant and Laptop. 1The detail introduction of this task can be seen at: http://alt.qcri.org/semeval2014/task4/ |
| Dataset Splits | No | Table 1 shows the training and test instance numbers in each category, but no explicit validation set split is mentioned or quantified. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU models, CPU types, or memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions the use of 'GloVe' for word embeddings but does not provide specific version numbers for any software dependencies or libraries. |
| Experiment Setup | Yes | In our experiments, all word embeddings from context and target are initialized by Glo Ve2 [Pennington et al., 2014], and all out-of-vocabulary words are initialized by sampling from the uniform distribution U( 0.1, 0.1). All weight matrices are given their initial values by sampling from uniform distribution U( 0.1, 0.1), and all biases are set to zeros. The dimensions of word embeddings, attention vectors and LSTM hidden states are set to 300 as in [Wang et al., 2016]. To train the parameters of IAN, we employ the Momentum [Qian, 1999], which adds a fraction γ of the update vector in the prior step to the current update vector. The coefficient of L2 normalization in the objective function is set to 10 5, and the dropout rate is set to 0.5. |