RNN Simulations of Grammaticality Judgments on Long-distance Dependencies

Shammur Absar Chowdhury, Roberto Zamparelli


Abstract
The paper explores the ability of LSTM networks trained on a language modeling task to detect linguistic structures which are ungrammatical due to extraction violations (extra arguments and subject-relative clause island violations), and considers its implications for the debate on language innatism. The results show that the current RNN model can correctly classify (un)grammatical sentences, in certain conditions, but it is sensitive to linguistic processing factors and probably ultimately unable to induce a more abstract notion of grammaticality, at least in the domain we tested.
Anthology ID:
C18-1012
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
133–144
Language:
URL:
https://aclanthology.org/C18-1012
DOI:
Bibkey:
Cite (ACL):
Shammur Absar Chowdhury and Roberto Zamparelli. 2018. RNN Simulations of Grammaticality Judgments on Long-distance Dependencies. In Proceedings of the 27th International Conference on Computational Linguistics, pages 133–144, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
RNN Simulations of Grammaticality Judgments on Long-distance Dependencies (Chowdhury & Zamparelli, COLING 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-bitext-workshop/C18-1012.pdf
Code
 LiCo-TREiL/Computational-Ungrammaticality