Cross Temporal Recurrent Networks for Ranking Question Answer Pairs
Authors: Yi Tay, Luu Anh Tuan, Siu Cheung Hui
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | To ascertain the effectiveness of our proposed approach, we conduct experiments on three popular benchmark datasets. |
| Researcher Affiliation | Collaboration | Yi Tay,1 Luu Anh Tuan,2 Siu Cheung Hui3 1,3 Nanyang Technological University School of Computer Science and Engineering, Singapore 2 Institute for Infocomm Research, Singapore |
| Pseudocode | No | The paper describes mathematical equations and processes, but does not provide structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper provides a link for dataset splits ('https://github.com/vanzytay/Yahoo QA Splits') but does not provide concrete access to the source code for the methodology described in this paper. |
| Open Datasets | Yes | Yahoo QA Yahoo Answers is a CQA platform. This is a moderately large dataset containing 142, 627 QA pairs which are obtained from the CQA platform. More specifically, preprocessing and testing splits1 are obtained from (Tay et al. 2017). Qatar Living This is another CQA dataset which was obtained from the popular Sem Eval-2016 Task 3 Subtask A (CQA). Trec QA This is a popular QA ranking benchmark obtained from the TREC QA Tracks 8-13. |
| Dataset Splits | Yes | The statistics of all datasets, i.e., training sets, development sets and testing sets, are given in Table 3. ...Early stopping is adopted and training is terminated if the validation performance doesn t improve after 5 epochs. |
| Hardware Specification | No | The paper discusses runtime comparisons and efficiency but does not provide specific hardware details (e.g., CPU, GPU models, or memory specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions 'Adam Optimizer' and 'Glo VE embeddings' but does not provide specific version numbers for software dependencies. |
| Experiment Setup | Yes | For our CTRN model, we tune the output dimension (number of filters) within [128, 1024] in multiples of 128. A single layered CTRN and QRNN is used. The number of dense (MLP) layers is tuned from [1, 3] and learning rate tuned amongst {10 3, 10 4, 10 5}. Batch size is tuned amongst {64, 128, 256, 512}. Dropout is set to 0.5 and L2 regularization is set to 4 10 6. |