Imagination-Augmented Natural Language Understanding

Yujie Lu, Wanrong Zhu, Xin Wang, Miguel Eckstein, William Yang Wang


Abstract
Human brains integrate linguistic and perceptual information simultaneously to understand natural language, and hold the critical ability to render imaginations. Such abilities enable us to construct new abstract concepts or concrete objects, and are essential in involving practical knowledge to solve problems in low-resource scenarios. However, most existing methods for Natural Language Understanding (NLU) are mainly focused on textual signals. They do not simulate human visual imagination ability, which hinders models from inferring and learning efficiently from limited data samples. Therefore, we introduce an Imagination-Augmented Cross-modal Encoder (iACE) to solve natural language understanding tasks from a novel learning perspective—imagination-augmented cross-modal understanding. iACE enables visual imagination with external knowledge transferred from the powerful generative and pre-trained vision-and-language models. Extensive experiments on GLUE and SWAG show that iACE achieves consistent improvement over visually-supervised pre-trained models. More importantly, results in extreme and normal few-shot settings validate the effectiveness of iACE in low-resource natural language understanding circumstances.
Anthology ID:
2022.naacl-main.326
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4392–4402
Language:
URL:
https://aclanthology.org/2022.naacl-main.326
DOI:
10.18653/v1/2022.naacl-main.326
Bibkey:
Cite (ACL):
Yujie Lu, Wanrong Zhu, Xin Wang, Miguel Eckstein, and William Yang Wang. 2022. Imagination-Augmented Natural Language Understanding. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4392–4402, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Imagination-Augmented Natural Language Understanding (Lu et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.326.pdf
Code
 yujielu10/iace-nlu
Data
GLUEMRPCMultiNLIQNLISSTSWAG