Coherence is an important aspect of text quality and is crucial for ensuring its readability. One important limitation of existing coherence models is that training on one domain does not easily generalize to unseen categories of text. Previous work advocates for generative models for cross-domain generalization, because for discriminative models, the space of incoherent sentence orderings to discriminate against during training is prohibitively large.

In this work, we propose a local discriminative neural model with a much smaller negative sampling space that can efficiently learn against incorrect orderings. The proposed coherence model is simple in structure, yet it significantly outperforms previous state-of-the-art methods on a standard benchmark dataset on the Wall Street Journal corpus, as well as in multiple new challenging settings of transfer to unseen categories of discourse on Wikipedia articles.

Code and dataset here.

Authors
BibTeX
@InProceddings{xu2019cross,
author = {Xu, Peng and Saghir, Hamidreza and Kang, Jin Sung and Long, Teng and Bose, Avishek Joey and Cao,
Yanshuai and Cheung, Jackie Chi Kit},
title = {A Cross-Domain Transferable Neural Coherence Model}
booktitle = {The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019)},
month = {July},
year = {2019},
publisher = {ACL}
}