An extractive text summarizer with a tf-idf driven topic selection algorithm, controlled by compression extent specified by the user.
- Python 3.7
The script takes a single input text file with individual sentences in Hindi unicode (utf-8) in each line, and the desired compression pecentage (stable compression range: 50% - 99%).
python3 hindi_summarizer.py <input_file_path.txt> <output_percentage>
Eg.
python3 hindi_summarizer.py sample_input_1.txt 75 # summary saved to output.txt
KV Aditya Srivatsa (k.v.aditya@research.iiit.ac.in)
If you have any queries, please do reach out.
Refer to the LICENSE file for more details.