Nothing Special   »   [go: up one dir, main page]

Systematic Generalization on gSCAN with Language Conditioned Embedding

Tong Gao, Qi Huang, Raymond Mooney


Abstract
Systematic Generalization refers to a learning algorithm’s ability to extrapolate learned behavior to unseen situations that are distinct but semantically similar to its training data. As shown in recent work, state-of-the-art deep learning models fail dramatically even on tasks for which they are designed when the test set is systematically different from the training data. We hypothesize that explicitly modeling the relations between objects in their contexts while learning their representations will help achieve systematic generalization. Therefore, we propose a novel method that learns objects’ contextualized embeddings with dynamic message passing conditioned on the input natural language and end-to-end trainable with other downstream deep learning modules. To our knowledge, this model is the first one that significantly outperforms the provided baseline and reaches state-of-the-art performance on grounded SCAN (gSCAN), a grounded natural language navigation dataset designed to require systematic generalization in its test splits.
Anthology ID:
2020.aacl-main.49
Volume:
Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
Month:
December
Year:
2020
Address:
Suzhou, China
Editors:
Kam-Fai Wong, Kevin Knight, Hua Wu
Venue:
AACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
491–503
Language:
URL:
https://aclanthology.org/2020.aacl-main.49
DOI:
Bibkey:
Cite (ACL):
Tong Gao, Qi Huang, and Raymond Mooney. 2020. Systematic Generalization on gSCAN with Language Conditioned Embedding. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 491–503, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Systematic Generalization on gSCAN with Language Conditioned Embedding (Gao et al., AACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.aacl-main.49.pdf
Code
 HQ01/gSCAN_with_language_conditioned_embedding +  additional community code
Data
GSCANSCAN