PSYCHIC: A Neuro-Symbolic Framework for Knowledge Graph Question-Answering Grounding
This work addresses the problem of knowledge graph question-answering for researchers and practitioners in semantic web, but it is incremental as it builds on existing neuro-symbolic approaches.
The authors tackled question answering over knowledge graphs by proposing a neuro-symbolic framework called PSYCHIC, which achieved an F1 score of 0.18% on question answering and 71.00% on entity linking, placing third in the latter.
The Scholarly Question Answering over Linked Data (Scholarly QALD) at The International Semantic Web Conference (ISWC) 2023 challenge presents two sub-tasks to tackle question answering (QA) over knowledge graphs (KGs). We answer the KGQA over DBLP (DBLP-QUAD) task by proposing a neuro-symbolic (NS) framework based on PSYCHIC, an extractive QA model capable of identifying the query and entities related to a KG question. Our system achieved a F1 score of 00.18% on question answering and came in third place for entity linking (EL) with a score of 71.00%.