SemEval2024-STR

Welcome to the SemEval 2024 Task 1: Semantic Textual Relatedness (STR) instructions repository. This repository is designed to guide participants through the task, providing resources, source code, and essential documentation for effective participation.

Directory

• res - Resources including datasets, model weights, and experiment records
• src - Source code including methods, models, trainers, and utility functions
• main.py - The primary Python script to execute tasks and run experiments
• config.py - Configuration file containing essential settings

Dependencies

• Python >= 3.11.7
• jupyterlab >= 4.0.9
• numpy >= 1.26.2
• pandas >= 2.1.4

Setup

Please ensure the required packages are already installed. A virtual environment is recommended.

$ cd SemEval2024-STR
$ pip install pip --upgrade
$ pip install jupyterlab
$ pip install -r requirements.txt

To open the instructional Jupyter Notebook:

$ jupyter lab

To execute the main script and generate results:

$ python main.py

Authors

• Ning Shi - ning.shi@ualberta.ca

References

• SemEval 2024 Task 1: Semantic Textual Relatedness (STR).
  Dataset | Languages | Shared Task Starter Kit | Citing This Work