Sentence simplification with iSimp and Daniel Gutiérrez's algorithm

About iSimp

We employ iSimp available in https://research.bioinformatics.udel.edu/isimp/

Peng,Y., Tudor,C., Torii,M., Wu,C.H., Vijay-Shanker,K. (2012) iSimp: A Sentence Simplification System for Biomedical Text. In Proceedings of the 2012 IEEE International Conference on Bioinformatics and Biomedicine. 211-216.

Directories

iSimp

/isimp_v2

Temporal iSimp files with constructs

/iSimp_sentences

Final simplified sentences

/algorithm_sentences

Cleaned sentences

format/sanitized_sentences

Separated sentences one per file

format/split_sentences

Scripts

Clean sentences for iSimp

Usage: python3 ./format/regex.py <input_file_path> <output_file_path>
python3 ./format/regex.py ./input-sentences/input-sentences.txt ./format/sanitized_sentences/input-sentences.txt

Main shell script for sentence simplification

./sentence-simplification-main.sh
Usage: ./sentence-simplification-main.sh <input_path> <output_file_path>
./sentence-simplification/sentence-simplification-main.sh ./format/split_sentences ./algorithm_sentences/filename.txt
<input_path> Path for cleaned and separated sentences, one per file.
<output_file_path> Path and filename. It uses filename to create files with simplified sentences and with an index within the filename.
**Requirements**: sentences must be separated one per file and they must be cleaned.
It calls simplifier.py

Python scritp for sentences simplification

simplifier.py
It is called by sentence-simplification-main.sh