Files
Castor/sm_modified_cnn/create_dataset.sh
T
rosequ 36b1ddb858 SM model for WikiQA (#63) (#64)
* support for WikiQA dataset

* parallel runs for both datasets

* minor fixes

* updated README

* removed data folder; added scripts to create dataset; updated README

* after CR

* after CR2
2017-10-04 15:59:26 -04:00

17 lines
870 B
Bash
Executable File

#!/bin/sh
mkdir -p data
python overlap_features.py --dir ../../data/TrecQA/
CURRENT_DIR=$(pwd)
cd ../../data/TrecQA
cd raw-dev/; paste id.txt sim.txt a.toks b.toks overlap_feats.txt > $CURRENT_DIR/data/trecqa.dev.tsv; cd ..
cd raw-test/; paste id.txt sim.txt a.toks b.toks overlap_feats.txt > $CURRENT_DIR/data/trecqa.test.tsv; cd ..
cd train-all/; paste id.txt sim.txt a.toks b.toks overlap_feats.txt > $CURRENT_DIR/data/trecqa.train.tsv; cd ..
cd $CURRENT_DIR
python overlap_features.py --dir ../../data/WikiQA/
cd ../../data/WikiQA
cd dev/; paste id.txt sim.txt a.toks b.toks overlap_feats.txt > $CURRENT_DIR/data/wikiqa.dev.tsv; cd ..
cd test/; paste id.txt sim.txt a.toks b.toks overlap_feats.txt > $CURRENT_DIR/data/wikiqa.test.tsv; cd ..
cd train/; paste id.txt sim.txt a.toks b.toks overlap_feats.txt > $CURRENT_DIR/data/wikiqa.train.tsv; cd ..
cd $CURRENT_DIR