Language Modeling with a General Second-Order RNN

Diego Maupomé, Marie-Jean Meurs


Abstract
Different Recurrent Neural Network (RNN) architectures update their state in different manners as the input sequence is processed. RNNs including a multiplicative interaction between their current state and the current input, second-order ones, show promising performance in language modeling. In this paper, we introduce a second-order RNNs that generalizes existing ones. Evaluating on the Penn Treebank dataset, we analyze how its different components affect its performance in character-lever recurrent language modeling. We perform our experiments controlling the parameter counts of models. We find that removing the first-order terms does not hinder performance. We perform further experiments comparing the effects of the relative size of the state space and the multiplicative interaction space on performance. Our expectation was that a larger states would benefit language models built on longer documents, and larger multiplicative interaction states would benefit ones built on larger input spaces. However, our results suggest that this is not the case and the optimal relative size is the same for both document tokenizations used.
Anthology ID:
2020.lrec-1.584
Volume:
Proceedings of the Twelfth Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
4749–4753
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.584
DOI:
Bibkey:
Cite (ACL):
Diego Maupomé and Marie-Jean Meurs. 2020. Language Modeling with a General Second-Order RNN. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4749–4753, Marseille, France. European Language Resources Association.
Cite (Informal):
Language Modeling with a General Second-Order RNN (Maupomé & Meurs, LREC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lrec-1.584.pdf