cs-vojna-i-mir

A (computational) linguistic analysis of code-switching Russian-French in Lev Tolstoi's Война и мир (War and Peace).

Installation

To create a virtual environment and install all required packages, run bash install.sh. Download the dataset from WikiSource and place the .txt files in a directory corpus.

Usage

scripts:

• preprocess.py: data preprocessing and computing CS types -> creates cs_*.csv
• codeswitch.py: annotate intrasentential CS instances with PoS tags, lemmata, dependency and morphological information -> creates features.csv
• analysis.ipynb: analyse outputs

outputs:

• cs_*.csv: overview of CS instances of each volume
• features.csv: linguistic features of intra-sentential CS instances