Compositional Generalization for Primitive Substitutions

Yuanpeng Li, Liang Zhao, Jianyu Wang, Joel Hestness


Abstract
Compositional generalization is a basic mechanism in human language learning, but current neural networks lack such ability. In this paper, we conduct fundamental research for encoding compositionality in neural networks. Conventional methods use a single representation for the input sentence, making it hard to apply prior knowledge of compositionality. In contrast, our approach leverages such knowledge with two representations, one generating attention maps, and the other mapping attended input words to output symbols. We reduce the entropy in each representation to improve generalization. Our experiments demonstrate significant improvements over the conventional methods in five NLP tasks including instruction learning and machine translation. In the SCAN domain, it boosts accuracies from 14.0% to 98.8% in Jump task, and from 92.0% to 99.7% in TurnLeft task. It also beats human performance on a few-shot learning task. We hope the proposed approach can help ease future research towards human-level compositional language learning.
Anthology ID:
D19-1438
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:
4293–4302
Language:
URL:
https://aclanthology.org/D19-1438
DOI:
10.18653/v1/D19-1438
Bibkey:
Cite (ACL):
Yuanpeng Li, Liang Zhao, Jianyu Wang, and Joel Hestness. 2019. Compositional Generalization for Primitive Substitutions. 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 4293–4302, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Compositional Generalization for Primitive Substitutions (Li et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1438.pdf
Attachment:
 D19-1438.Attachment.zip
Code
 yli1/CGPS
Data
SCAN