Automatic metric - ROUGE

Main leaderboard according to ROUGE score. Manual evaluation results will be updated once available.
# Team R-1 R-2 R-LCS
1 harvardnlp 0.22 0.05 0.17
2 choi 0.19 0.04 0.15
3 kalinowski 0.20 0.04 0.15
4 baseline-model 0.03 0.0 0.02