Do RNNs learn human-like abstract word order preferences?

Richard Futrell, Roger P. Levy


Anthology ID:
W19-0106
Volume:
Proceedings of the Society for Computation in Linguistics (SCiL) 2019
Month:
Year:
2019
Address:
Editors:
Gaja Jarosz, Max Nelson, Brendan O’Connor, Joe Pater
Venue:
SCiL
SIG:
Publisher:
Note:
Pages:
50–59
Language:
URL:
https://aclanthology.org/W19-0106
DOI:
10.7275/jb34-9986
Bibkey:
Cite (ACL):
Richard Futrell and Roger P. Levy. 2019. Do RNNs learn human-like abstract word order preferences?. In Proceedings of the Society for Computation in Linguistics (SCiL) 2019, pages 50–59.
Cite (Informal):
Do RNNs learn human-like abstract word order preferences? (Futrell & Levy, SCiL 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-0106.pdf
Code
 langprocgroup/rnn_soft_constraints
Data
Billion Word BenchmarkOne Billion Word Benchmark