Adaptive Semantic Compositionality for Sentence Modelling
Authors: Pengfei Liu, Xipeng Qiu, Xuanjing Huang
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our model on five datasets of sentiment classification and demonstrate its efficacy with qualitative and quantitative experimental analysis. |
| Researcher Affiliation | Academia | Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University 825 Zhangheng Road, Shanghai, China {pfliu14,xpqiu,xjhuang}@fudan.edu.cn |
| Pseudocode | No | The paper provides mathematical equations for its models but does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any concrete access information (e.g., repository link, explicit statement of code release, or mention of code in supplementary materials) for the source code of the described methodology. |
| Open Datasets | Yes | We use the dataset proposed by [Williams et al., 2015]... MR The movie reviews with two classes [Pang and Lee, 2005]... SST-1 The movie reviews with five classes (negative, somewhat negative, neutral, somewhat positive, positive) in the Stanford Sentiment Treebank2 [Socher et al., 2013]... SST-2 The movie reviews with binary classes. It is also from the Stanford Sentiment Treebank. SUBJ Subjectivity data set where the goal is to classify each instance (snippet) as being subjective or objective. [Pang and Lee, 2004] and footnote 2: http://nlp.stanford.edu/sentiment. |
| Dataset Splits | Yes | Dataset Train Dev. Test... MR 9596 1066... SST-1 8544 1101 2210... SST-2 6920 872 1821... SUBJ 9000 1000... (from Table 4) and For each task, we take the hyperparameters which achieve the best performance on the development set via an small grid search over combinations of the initial learning rate [0.1, 0.01, 0.001], l2 regularization [0.0, 5E 5, 1E 5] and the values of L [3, 4, 5, 6]. |
| Hardware Specification | No | The paper does not explicitly describe the specific hardware (e.g., GPU/CPU models, memory) used to run its experiments. |
| Software Dependencies | No | The paper mentions tools and algorithms like 'word2vec' and 'Ada Grad' with citations, but it does not provide specific software library names with version numbers (e.g., 'PyTorch 1.x', 'TensorFlow 2.x') for reproducibility. |
| Experiment Setup | Yes | Initialization and Hyperparameters In all of our experiments, the word and phrase embeddings are trained using word2vec [Mikolov et al., 2013] on the Wikipedia corpus (1B words). The other parameters are initialized by randomly sampling from uniform distribution in [ 0.1, 0.1]... For each task, we take the hyperparameters which achieve the best performance on the development set via an small grid search over combinations of the initial learning rate [0.1, 0.01, 0.001], l2 regularization [0.0, 5E 5, 1E 5] and the values of L [3, 4, 5, 6]. The final hyper-parameters are as follows. For the idiom-enriched dataset, the size of pretrained embedding is 300 while the size of hidden state is 200. The initial learning rate is 0.01. The regularization weight of the parameters is 10 5. For the other datasets, the sizes of pre-trained embeddings and hidden states are both set as 300. The initial learning rate is 0.1. The regularization weight of the parameters is 0. Besides, the value of L is set to 4 for all datasets. |