Aligning Learning Outcomes to Learning Resources: A Lexico-Semantic Spatial Approach
Authors: Swarnadeep Saha, Malolan Chetlur, Tejas Indulal Dhamecha, W M Gayathri K Wijayarathna, Red Mendoza, Paul Gagnon, Nabil Zary, Shantanu Godbole
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We empirically establish the importance of the lexical, semantic, and spatial models within the proposed approach. We evaluate the effectiveness of our approach for the page relevancy task as well as the final LO alignment task using both standard metrics and a novel Click metric. |
| Researcher Affiliation | Collaboration | 1IBM Research India 2Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore |
| Pseudocode | No | The paper describes its models and approach textually and with block diagrams (Figure 3, Figure 4) but does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions using a third-party library, "Pdf Box1 java library", with a link to its repository, but it does not state that the authors are releasing their own code for the work described in the paper. |
| Open Datasets | No | The paper refers to the dataset as "Our dataset" and describes its characteristics, but it does not provide concrete access information (link, DOI, specific repository, or formal citation to a public dataset) for public availability. |
| Dataset Splits | No | The paper specifies a train-test split ("75 LRs for training and 25 for testing") but does not explicitly mention or provide details for a separate validation split. Table 1 only lists training and testing samples. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU models, CPU models, or memory specifications used for running the experiments. |
| Software Dependencies | No | The paper mentions using the "Pdf Box1 java library" and "250-dimensional embeddings, pre-trained on the Pub Med corpus", but it does not provide specific version numbers for the Pdf Box library or any other key software components used in the implementation. |
| Experiment Setup | Yes | In our experiments, we choose k = 1. We choose the number of bins as 10 with bin size 0.1. All word vectors are initialized with 250-dimensional embeddings, pre-trained on the Pub Med corpus and further updated for our task. Our final model is a siamese network i.e. we use the same text encoder with the same weights to encode the LO, the title, and the body. |