A Neural Local Coherence Model
By Tien Dat Nguyen, Shafiq R. Joty. 2017
83 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yuxiang Wu
- Giuseppe Riccardi
- Evgeny A. Stepanov
- Alessandra Cervone
- Baotian Hu
- Hinrich Schütze
- Zhiyuan Liu
- Xipeng Qiu
In Natural Language Processing
- Yuxiang Wu
- Giuseppe Riccardi
- Evgeny A. Stepanov
- Alessandra Cervone
- Baotian Hu
- Hang Li
- Fei Liu
- Kristjan Arumae
Citations in the corpus
- Learning to Extract Coherent Summary via Deep Reinforcement Learning (2018, background): “(Nguyen and Joty 2017) presented a local coherence model based on a convolutional neural network that operates over the distributed representation of entity grid.”
- Coherence Models for Dialogue (2018, methodology): “The state of the art for these tasks was recently achieved by [30], which uses the entity grid as input to a Convolutional Neural Network.”