Self-Adaptive Hierarchical Sentence Model
Authors: Han Zhao, Zhengdong Lu, Pascal Poupart
IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Both qualitative and quantitative analysis shows that Ada Sent can automatically form and select the representations suitable for the task at hand during training, yielding superior classification performance over competitor models on 5 benchmark data sets. |
| Researcher Affiliation | Collaboration | David R. Cheriton School of Computer Science, University of Waterloo, ON, Canada Noah s Ark Lab, Huawei Technologies, Shatin, Hong Kong {han.zhao, ppoupart}@uwaterloo.ca, lu.zhengdong@huawei.com |
| Pseudocode | No | The paper describes the model using mathematical equations and figures, but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not state that the code for Ada Sent is open-source, nor does it provide a link to such code. It only references a public implementation for 'P.V.' a competitor model. |
| Open Datasets | Yes | MR. Movie reviews [Pang and Lee, 2005]1 data set where each instance is a sentence. The objective is to classify each review by its overall sentiment polarity, either positive or negative. 1https://www.cs.cornell.edu/people/pabo/movie-review-data/ CR. Annotated customer reviews of 14 products obtained from Amazon [Hu and Liu, 2004]2. The task is to classify each customer review into positive and negative categories. 2http://www.cs.uic.edu/ liub/FBS/sentiment-analysis.html SUBJ. Subjectivity data set where the goal is to classify each instance (snippet) as being subjective or objective [Pang and Lee, 2004]. MPQA. Phrase level opinion polarity detection subtask of the MPQA data set [Wiebe et al., 2005]3. 3http://mpqa.cs.pitt.edu/ TREC. Question data set, in which the goal is to classify an instance (question) into 6 different types [Li and Roth, 2002]4. 4http://cogcomp.cs.illinois.edu/Data/QA/QC/ |
| Dataset Splits | Yes | For datasets which do not provide an explicit split of train/test, we use 10-fold cross-validation (CV) instead. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments, such as GPU or CPU models. |
| Software Dependencies | No | The paper mentions using 'word2vec [Mikolov et al., 2013]' but does not provide specific version numbers for this or any other software dependencies. |
| Experiment Setup | Yes | The paper specifies a regularization coefficient λ ranging from '0.01 to 5 10 5', states the use of 'minibatch Ada Grad with the norm-clipping technique' for optimization, and describes 'a 50-dimensional word embedding' along with the use of 'hyperbolic tangent function as the activation function' and 'MLP to implement the classifier' and 'softmax function to implement the gating network'. |