About
This resource contains the source code of “A Unified Neural Coherence Model” paper (EMNLP-IJCNLP 2019, Hong Kong, China).
Source code
Datasets
Regard to WSJ license, we only share the script to generate local and global coherence dataset from the WSJ dataset.
Citation
Please cite our paper if you found the resources in this repository useful.
@inproceedings{moon-etal-2019-unified,
title = "A Unified Neural Coherence Model",
author = "Moon, Han Cheol and
Mohiuddin, Tasnim and
Joty, Shafiq and
Xu, Chi",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/D19-1231",
doi = "10.18653/v1/D19-1231",
pages = "2262--2272"
}
Licence
MIT licence.