https://github.com/jxwuyi/atnre
Adversarial Training for Neural Relation Extraction
https://github.com/jxwuyi/atnre
adversarial-machine-learning nlp-machine-learning relation-extraction tensorflow-experiments
Last synced: about 1 year ago
JSON representation
Adversarial Training for Neural Relation Extraction
- Host: GitHub
- URL: https://github.com/jxwuyi/atnre
- Owner: jxwuyi
- License: bsd-3-clause
- Created: 2017-07-21T03:58:07.000Z (almost 9 years ago)
- Default Branch: master
- Last Pushed: 2018-06-03T03:49:24.000Z (almost 8 years ago)
- Last Synced: 2025-04-07T02:04:09.357Z (about 1 year ago)
- Topics: adversarial-machine-learning, nlp-machine-learning, relation-extraction, tensorflow-experiments
- Language: Python
- Size: 709 KB
- Stars: 109
- Watchers: 5
- Forks: 31
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# AtNRE: Adversarial training for Neural Relation Extraction
This repository is the source code for the [paper](https://people.eecs.berkeley.edu/~russell/papers/emnlp17-relation.pdf):
### Adversarial Training for Relation Extraction
*Yi Wu, David Bamman, Stuart Russell*
*University of California, Berkeley*
*Conference on Empirical Methods in Natural Language Processing (EMNLP) 2017, Copenhagen, Denmark.*
For data, please refer to the references in our paper and download from the original sources of the datasets.
*Original NYT dataset ([paper](http://aclweb.org/anthology/P16-1200), [link](https://github.com/thunlp/NRE))*
*Original NAACL dataset ([paper](https://aclweb.org/anthology/N/N16/N16-1104.pdf), [link](https://www.cs.washington.edu/ai/gated_instructions/naacl_data.zip))*
For reproducibility of our results, [here](https://people.eecs.berkeley.edu/~jxwuyi/data/AtNRE_processed_data.zip) is the processed pickled data used in the code. **PLEASE** (1) do not distributed and (2) refer to the original data sources for either personal use or academic purpose.
The code is under BSD-3 license.