MELINDA: A Multimodal Dataset for Biomedical Experiment Method Classification
Authors: Te-Lin Wu, Shikhar Singh, Sayan Paul, Gully Burns, Nanyun Peng14076-14084
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We benchmark various state-of-the-art NLP and computer vision models, including unimodal models which only take either caption texts or images as inputs, and multimodal models. Extensive experiments and analysis show that multimodal models, despite outperforming unimodal ones, still need improvements especially on a less-supervised way of grounding visual concepts with languages, and better transferability to low resource domains. We release our dataset and the benchmarks to facilitate future research in multimodal learning, especially to motivate targeted improvements for applications in scientific domains. |
| Researcher Affiliation | Collaboration | Te-Lin Wu1, Shikhar Singh2, Sayan Paul3, Gully Burns4, Nanyun Peng1 1 University of California, Los Angeles, 2 University of Southern California 3 Intuit Inc., 4 Chan Zuckerberg Initiative |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks (e.g., clearly labeled algorithm sections or code-like formatted procedures). |
| Open Source Code | Yes | More details of our data collection pipeline can be found in the appendix and our released code repository7. 7The data collection pipeline and our benchmark models can be found at https://github.com/PlusLabNLP/melinda. |
| Open Datasets | Yes | We introduce a new dataset, MELINDA, for Multimodal biom Edica L exper Ime Nt metho D cl Assiļ¬cation. ... We release our dataset and the benchmarks to facilitate future research in multimodal learning, especially to motivate targeted improvements for applications in scientific domains. |
| Dataset Splits | Yes | We split the whole dataset into three subsets: train, validation, and test sets, with a ratio of 80% 10% 10%. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions specific language models and embeddings used (e.g., Bio-GloVe, BERT, SciBERT, RoBERTa), but it does not specify software dependencies with version numbers (e.g., Python version, specific deep learning framework versions like PyTorch 1.x or TensorFlow 2.x). |
| Experiment Setup | No | The paper mentions model architectures and fine-tuning strategies (e.g., fine-tuning the final three ResNet blocks, experimenting with MLM objectives), but it does not provide specific experimental setup details such as concrete hyperparameter values (e.g., learning rate, batch size, number of epochs) or optimizer settings. |