Retrodiction as Delayed Recurrence: the Case of Adjectives in Italian and English

Raquel G. Alhama, Francesca Zermiani, Atiqah Khaliq


Abstract
We address the question of how to account for both forward and backward dependencies in an online processing account of human language acquisition. We focus on descriptive adjectives in English and Italian, and show that the acquisition of adjectives in these languages likely relies on tracking both forward and backward regularities. Our simulations confirm that forward-predicting models like standard Recurrent Neural Networks (RNN) cannot account for this phenomenon due to the lack of backward prediction, but the addition of a small delay (as proposed in Turek et al., 2019) endows the RNN with the ability to not only predict but also retrodict.
Anthology ID:
2021.alta-1.17
Volume:
Proceedings of the The 19th Annual Workshop of the Australasian Language Technology Association
Month:
December
Year:
2021
Address:
Online
Venue:
ALTA
SIG:
Publisher:
Australasian Language Technology Association
Note:
Pages:
163–168
Language:
URL:
https://aclanthology.org/2021.alta-1.17
DOI:
Bibkey:
Cite (ACL):
Raquel G. Alhama, Francesca Zermiani, and Atiqah Khaliq. 2021. Retrodiction as Delayed Recurrence: the Case of Adjectives in Italian and English. In Proceedings of the The 19th Annual Workshop of the Australasian Language Technology Association, pages 163–168, Online. Australasian Language Technology Association.
Cite (Informal):
Retrodiction as Delayed Recurrence: the Case of Adjectives in Italian and English (Alhama et al., ALTA 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.alta-1.17.pdf
Code
 rgalhama/retro_adjs