Systematic Generalization on gSCAN with Language Conditioned Embedding

September 11, 2020 Β· Declared Dead Β· πŸ› AACL

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Tong Gao, Qi Huang, Raymond J. Mooney arXiv ID 2009.05552 Category cs.AI: Artificial Intelligence Cross-listed cs.CL Citations 22 Venue AACL Last Checked 4 months ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted