Multiattentive Recurrent Neural Network Architecture for Multilingual Readability Assessment

Ion Madrazo Azpiazu, Maria Soledad Pera


Abstract
We present a multiattentive recurrent neural network architecture for automatic multilingual readability assessment. This architecture considers raw words as its main input, but internally captures text structure and informs its word attention process using other syntax- and morphology-related datapoints, known to be of great importance to readability. This is achieved by a multiattentive strategy that allows the neural network to focus on specific parts of a text for predicting its reading level. We conducted an exhaustive evaluation using data sets targeting multiple languages and prediction task types, to compare the proposed model with traditional, state-of-the-art, and other neural network strategies.
Anthology ID:
Q19-1028
Volume:
Transactions of the Association for Computational Linguistics, Volume 7
Month:
Year:
2019
Address:
Cambridge, MA
Editors:
Lillian Lee, Mark Johnson, Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
421–436
Language:
URL:
https://aclanthology.org/Q19-1028
DOI:
10.1162/tacl_a_00278
Bibkey:
Cite (ACL):
Ion Madrazo Azpiazu and Maria Soledad Pera. 2019. Multiattentive Recurrent Neural Network Architecture for Multilingual Readability Assessment. Transactions of the Association for Computational Linguistics, 7:421–436.
Cite (Informal):
Multiattentive Recurrent Neural Network Architecture for Multilingual Readability Assessment (Azpiazu & Pera, TACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/Q19-1028.pdf
Code
 ionmadrazo/Vec2Read