A Hard Look at Soft Concepts
Authors: Dafna Shahaf
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present two approaches for tackling such challenges an axiomatic one and a data-driven one and demonstrate our ideas on two real-world applications: finding narratives in large textual corpora and identifying humorous cartoon captions. Evaluating metro maps is difficult, as ground truth is hard to define. Since the goal of the maps is to help people navigate through information, we conducted an extensive set of user studies to better understand the value of the methodology. Map users outperformed Google Scholar users in every parameter: Precision (84.5% to 74.2%), recall (73.1% to 46.4%) and number of seminal papers found (1.62 to 1.2). Our classifier achieves 69% accuracy for captions hinging on the same joke, and 64% accuracy comparing any two captions. |
| Researcher Affiliation | Academia | Dafna Shahaf The Hebrew University of Jerusalem dshahaf@cs.huji.ac.il |
| Pseudocode | No | The paper describes algorithms and formulations but does not include any explicitly labeled pseudocode blocks or algorithms. |
| Open Source Code | No | The paper does not provide any statements about releasing open-source code or links to a code repository for the methodology described. |
| Open Datasets | No | For our task, we create a dataset of crowdsourced New Yorker competition captions, along with human judgments. The paper describes creating its own dataset but does not provide any concrete access information (link, DOI, citation for public access) for it. |
| Dataset Splits | No | The paper discusses data collection and evaluation metrics but does not specify exact training, validation, or test dataset splits (e.g., percentages or sample counts). |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used to run the experiments, such as CPU or GPU models, or memory. |
| Software Dependencies | No | The paper describes the methods and applications but does not list any specific software dependencies or their version numbers (e.g., programming languages, libraries, or frameworks). |
| Experiment Setup | No | The paper describes the approaches and applications but does not provide specific experimental setup details, such as hyperparameters (e.g., learning rates, batch sizes), optimization settings, or other training configurations. |