gloryodeyemi/COMP_8730_Project

Summarization of English-Yoruba tweets with code-switches # Summarization of English-Yoruba Tweets with Code-Switches The goal of this experiment is to summarize tweets with English and Yoruba code switches. **Keywords:** Code-Switching, Tweet Summarization, Language Identification, Code-switching Detection, Translation, Natural Language Processing. ## The Data The twitter_data csv file has three columns: * **Tweets:** Tweets with code-switches. * **Eng_source:** English source of the tweets. * **Summary:** Human annotated summary of the tweets. ## Requirements You can find the modules and libraries used in this project in the requirement.txt file. You can also run the code below. ``` pip install -r requirements.txt ``` ## Structure * **Data:** contains the data file used for this project. * **utils:** contains the essential functions used for the project. * **data_analysis.ipynb:** A python notebook that uses the function in the utils to analyse the data used in this project. The results gives information about the data. * **data_collection.ipynb:** A python notebook that shows you the procedure of collecting tweets from Twitter using the Twitter API and tweepy python library. * **quick_start.ipynb:** A python notebook that shows a successful run of the project using the quickstart guideline. * **main.ipynb and main.py** are python notebook and script that utilizes the functions in utils to show the procedure of summarizing tweets with English-Yoruba code switches and the result gotten. ## Quickstart Guideline 1. Clone the repository ``` git clone github.com ``` 2. Change the directory to the cloned repository folder ``` %cd .../COMP_8730_Project ``` 3. Install the needed packages ``` pip install -r requirements.txt ``` 4. Run the script ``` python main.py ``` ## Baseline The Huggingface AutoTrain feature was used to train and evaluate the baseline approach on our dataset. The evaluation metric scores and testing interface can be found here. ## License This project is …