Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Earlier Attention? Aspect-Aware LSTM for Aspect-Based Sentiment Analysis
Authors: Bowen Xing, Lejian Liao, Dandan Song, Jingang Wang, Fuzheng Zhang, Zhongyuan Wang, Heyan Huang
IJCAI 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on Sem Eval-2014 Datasets demonstrate the effectiveness of AA-LSTM. |
| Researcher Affiliation | Collaboration | Bowen Xing1 , Lejian Liao1 , Dandan Song1 , Jingang Wang 2 , Fuzhen Zhang2 , Zhongyuan Wang2 and Heyan Huang1 1Lab of High Volume language Information Processing & Cloud Computing Beijing Lab of Intelligent Information Technology School of Computer Science & Technology, Beijing Institute of Technology 2Meituan-Dianping Group |
| Pseudocode | No | The paper provides mathematical equations (1-9) for the AA-LSTM network but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any concrete access (link or explicit statement of release) to open-source code for the methodology described. |
| Open Datasets | Yes | We experiment on Sem Eval 2014 [Pontiki et al., 2014] task 4 datasets which consist of laptop and restaurant reviews and are widely used benchmarks in many previous works |
| Dataset Splits | Yes | 20% of the training data is used as the development set. |
| Hardware Specification | No | The paper does not explicitly describe the specific hardware (e.g., CPU, GPU models) used for running its experiments. |
| Software Dependencies | No | The paper mentions software like TensorFlow, Glove, and Adam optimizer, but does not provide specific version numbers for these dependencies, which are necessary for reproducible descriptions. |
| Experiment Setup | Yes | All embedding dimensions are set to 300 and the batch size is set as 16. We minimize the loss function to train our models using Adam optimizer [Diederik and Jimmy, 2014] with the learning rate set as 0.001. To avoid over fitting, we adopt the dropout strategy with p = 0.5 and the coefficient of L2 normalization in the loss function is set to 0.01. |