Projects per year
Abstract
We provide a study of how induced model sparsity can help achieve compositional generalization and better sample efficiency in grounded language learning problems. We consider simple language-conditioned navigation problems in a grid world environment with disentangled observations. We show that standard neural architectures do not always yield compositional generalization. To address this, we design an agent that contains a goal identification module that encourages sparse correlations between words in the instruction and attributes of objects, composing them together to find the goal. The output of the goal identification module is the input to a value iteration network planner. Our agent maintains a high level of performance on goals containing novel combinations of properties even when learning from a handful of demonstrations. We examine the internal representations of our agent and find the correct correspondences between words in its dictionary and attributes in the environment.
Original language | English |
---|---|
Title of host publication | NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics |
Subtitle of host publication | Human Language Technologies, Proceedings of the Student Research Workshop |
Publisher | Association for Computational Linguistics |
Pages | 143-155 |
Number of pages | 13 |
ISBN (Electronic) | 978-1-955917-73-5 |
DOIs | |
Publication status | Published - 2022 |
MoE publication type | A4 Conference publication |
Event | Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Human Language Technologies - Seattle, United States Duration: 10 Jul 2022 → 15 Jul 2022 |
Conference
Conference | Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
---|---|
Abbreviated title | NAACL |
Country/Territory | United States |
City | Seattle |
Period | 10/07/2022 → 15/07/2022 |
Fingerprint
Dive into the research topics of 'Compositional Generalization in Grounded Language Learning via Induced Model Sparsity'. Together they form a unique fingerprint.Projects
- 1 Finished
-
-: Finnish Center for Artificial Intelligence
Kaski, S. (Principal investigator)
01/01/2019 → 31/12/2022
Project: Academy of Finland: Other research funding