Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons

Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, Zhaopeng Tu

Abstract
Recent studies have shown that a hybrid of self-attention networks (SANs) and recurrent neural networks RNNs outperforms both individual architectures, while not much is known about why the hybrid models work. With the belief that modeling hierarchical structure is an essential complementary between SANs and RNNs, we propose to further enhance the strength of hybrid models with an advanced variant of RNNs – Ordered Neurons LSTM (ON-LSTM), which introduces a syntax-oriented inductive bias to perform tree-like composition. Experimental results on the benchmark machine translation task show that the proposed approach outperforms both individual architectures and a standard hybrid model. Further analyses on targeted linguistic evaluation and logical inference tasks demonstrate that the proposed approach indeed benefits from a better modeling of hierarchical structure.
Anthology ID:
D19-1135
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1336–1341
Language:
URL:
https://aclanthology.org/D19-1135
DOI:
10.18653/v1/D19-1135
Bibkey:
Cite (ACL):
Jie Hao, Xing Wang, Shuming Shi, Jinfeng Zhang, and Zhaopeng Tu. 2019. Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1336–1341, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons (Hao et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/D19-1135.pdf
Attachment:
 D19-1135.Attachment.pdf
PDF Search Attachment