IBM Neuro-Symbolic AI Summer School Day 2: Question Answering (Pavan Kapanipathi)

NLP

NLU

knowledge graphs

conference

paper

AMR → triples → entity/relation linking → logic → LNN reasoner. SOTA on OALD and LC-QuAD.

Author

synesis

Published

August 12, 2022

IBM Neuro-Symbolic AI Summer School 2022. Image: LinkedIn.

IBM NeuroSymbolicAI Summer School 2022 Day 2: Neuro-symbolic Approaches for QuestionAnswering given by Pavan Kapanipathi:

Query -> AMR parse -> Triples -> Entity Linking -> Relation Linking -> Logic -> Reasoner
Reasoner: LNN (Logical Neural Networks)
SOTA on OALD and LC-OuAD

Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramón Fernández Astudillo, Maria Chang, et al. 2021. “Leveraging ABstract MEaning REpresentation for Knowledge Base Question Answering.” In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 3884–94. Online: Association for Computational Linguistics. https://aclanthology.org/2021.findings-acl.339/

Summer School site: https://ibm.github.io/neuro-symbolic-ai/events/ns-summerschool2022/

Originally posted on LinkedIn.