Manara - Qatar Research Repository
Browse
DOCUMENT
P17-1121.pdf (652.97 kB)
VIDEO
supp_P17-1121.mp4 (111.42 MB)
1/0
2 files

A Neural Local Coherence Model

conference contribution
submitted on 2024-09-22, 08:57 and posted on 2024-09-22, 15:35 authored by Dat Tien Nguyen, Shafiq Joty

We propose a local coherence model based on a convolutional neural network that operates over the entity grid representation of a text. The model captures long range entity transitions along with entity-specific features without loosing generalization, thanks to the power of distributed representation. We present a pairwise ranking method to train the model in an end-to-end fashion on a task and learn task-specific high level features. Our evaluation on three different coherence assessment tasks demonstrates that our model achieves state of the art results outperforming existing models by a good margin.

Other Information

Published in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
License: http://creativecommons.org/licenses/by/4.0/
See conference contribution on publisher's website: https://dx.doi.org/10.18653/v1/p17-1121

Conference information: 55th Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 518–523 Vancouver, Canada, July 30 - August 4, 2017

History

Language

  • English

Publisher

Association for Computational Linguistics

Publication Year

  • 2017

License statement

This Item is licensed under the Creative Commons Attribution 4.0 International License.

Institution affiliated with

  • Hamad Bin Khalifa University
  • Qatar Computing Research Institute - HBKU

Related Publications

Proceedings of the 55th Annual Meeting of the Association Computational Linguistics (Volume 1: Long Papers). (2017). https://doi.org/10.18653/v1/p17-1

Related Datasets

datienguyen (2017). cnn_coherence. Last modified 2018. GitHub Repository. https://github.com/datienguyen/cnn_coherence