A Neural Local Coherence Model for Text Quality Assessment

Mohsen Mesgar, Michael Strube


Abstract
We propose a local coherence model that captures the flow of what semantically connects adjacent sentences in a text. We represent the semantics of a sentence by a vector and capture its state at each word of the sentence. We model what relates two adjacent sentences based on the two most similar semantic states, each of which is in one of the sentences. We encode the perceived coherence of a text by a vector, which represents patterns of changes in salient information that relates adjacent sentences. Our experiments demonstrate that our approach is beneficial for two downstream tasks: Readability assessment, in which our model achieves new state-of-the-art results; and essay scoring, in which the combination of our coherence vectors and other task-dependent features significantly improves the performance of a strong essay scorer.
Anthology ID:
D18-1464
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4328–4339
Language:
URL:
https://aclanthology.org/D18-1464
DOI:
10.18653/v1/D18-1464
Bibkey:
Cite (ACL):
Mohsen Mesgar and Michael Strube. 2018. A Neural Local Coherence Model for Text Quality Assessment. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4328–4339, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
A Neural Local Coherence Model for Text Quality Assessment (Mesgar & Strube, EMNLP 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/fix-dup-bibkey/D18-1464.pdf
Attachment:
 D18-1464.Attachment.pdf
Video:
 https://preview.aclanthology.org/fix-dup-bibkey/D18-1464.mp4