Li, F, Hogg, DC orcid.org/0000-0002-6125-9564 and Cohn, AG orcid.org/0000-0002-7652-8907 (2022) Ontology Knowledge-enhanced In-Context Learning for Action-Effect Prediction. In: Advances in Cognitive Systems. Advances in Cognitive Systems 2022, 19-22 Nov 2022, Arlington, Virginia. ACS-2022
Abstract
Implementing human-level reasoning about action effects is an important competence for a cognitive agent: given precondition and action descriptions, a system should be able to infer the change in the physical world that the action causes. In this work, we propose a new action-effect prediction task. We explore few-shot learning with large pre-trained language models based on a limited number of samples and propose task-relevant ontology knowledge (from KnowRob ontology) integration for in-context learning with generative pre-trained transformer (GPT) models. Specifically, we develop an ontology-to-text transformation to bridge the gap between symbolic knowledge and text. We further introduce unseen knowledge learning via GPT-3 to infer knowledge for concepts that do not have definitions in the knowledge base. We evaluate our proposed method on two human-annotated datasets. Experimental results demonstrate that our approach can improve the performance of large-scale, state-of-the-art models on two action-effect prediction datasets.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 15 Dec 2022 16:44 |
Last Modified: | 15 Dec 2022 16:46 |
Published Version: | https://advancesincognitivesystems.github.io/acs20... |
Status: | Published |
Publisher: | ACS-2022 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:194133 |