Skip to content

SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning With Semantic Role Labeling

Notifications You must be signed in to change notification settings

amarasovic/naacl-mpqa-srl4orl

Folders and files

NameName
Last commit message
Last commit date

Latest commit

author
Ana Marasovic
Oct 10, 2018
5e0d339 · Oct 10, 2018

History

11 Commits
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Oct 10, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Apr 18, 2018
Apr 16, 2018
Apr 16, 2018
Apr 16, 2018
Aug 15, 2018

Repository files navigation

SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning With Semantic Role Labeling

This repository contains code for reproducing experiments done in:

Ana Marasovic and Anette Frank (2018): SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning With Semantic Role Labeling. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). New Orleans, USA.

Requirements

Data

ORL

Download MPQA 2.0 corpus.

Check mpqa2-pytools for example usage.

Splits can be found in the datasplit folder.

SRL

The data is provided by: CoNLL-2005 Shared Task, but the original words are from the Penn Treebank dataset, which is not publicly available.

How to train models?


python main.py --adv_coef 0.0 --model fs --exp_setup_id new --n_layers_orl 0 --begin_fold 0 --end_fold 4

python main.py --adv_coef 0.0 --model html --exp_setup_id new --n_layers_orl 1 --n_layers_shared 2 --begin_fold 0 --end_fold 4

python main.py --adv_coef 0.0 --model sp --exp_setup_id new --n_layers_orl 3 --begin_fold 0 --end_fold 4

python main.py --adv_coef 0.1 --model asp --exp_setup_id prior --n_layers_orl 3 --begin_fold 0 --end_fold 10

Reference

If you make use of the contents of this repository, please cite the following paper:

@inproceedings{marasovicfrank:srl4orl,
  title={{Improving Opinion Role Labeling Using Multi-Task Learning With Semantic Role Labeling}},
  author={Marasovi\'{c}, Ana and Frank, Anette},
  booktitle={Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)},
  year={2018},
  address={New Orleans, USA},
  note={to appear}
}