Adaptive Multi-Compositionality for Recursive Neural Models with Applications to Sentiment Analysis

Authors: Li Dong, Furu Wei, Ming Zhou, Ke Xu

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We integrate Ada MC into existing recursive neural models and conduct extensive experiments on the Stanford Sentiment Treebank. The results illustrate that Ada MC significantly outperforms state-of-the-art sentiment classification methods.
Researcher Affiliation Collaboration State Key Lab of Software Development Environment, Beihang University, Beijing, China Microsoft Research, Beijing, China
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not include an unambiguous statement about releasing source code for the described methodology or a direct link to a code repository.
Open Datasets Yes We evaluate the models on Stanford Sentiment Treebank1. This corpus contains the labels of syntactically plausible phrases... 1http://nlp.stanford.edu/sentiment/treebank.html
Dataset Splits Yes We use the standard dataset splits (train: 8,544, dev: 1,101, test: 2,210) in all the experiments.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running experiments.
Software Dependencies No The paper mentions 'Ada Grad' as an optimization algorithm, but does not provide specific software dependencies with version numbers.
Experiment Setup Yes We use the mini-batch version Ada Grad in our experiments with the batch size between 20 and 30. We employ f = tanh as the nonlinearity function. To initialize the parameters, we randomly sample values from a uniform distribution U ( , + ), where is a small value.