PSYCHIC: A Neuro-Symbolic Framework for Knowledge Graph Question-Answering Grounding

Hanna Abi Akl
10/19/2023
cs.AI

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

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%.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering

83% match2026

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

83% match1 repo6612021

Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey

82% match2023

Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering

82% match1 repo2026

Leveraging LLM-GNN Integration for Open-World Question Answering over Knowledge Graphs

82% match2026

Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases

82% match1 repo1722019

Cite this paper

@article{akl2023psychic,
  title  = {PSYCHIC: A Neuro-Symbolic Framework for Knowledge Graph Question-Answering Grounding},
  author = {Hanna Abi Akl},
  year   = {2023},
  eprint = {2310.12638},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.12638v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.12638.svg)](https://codeofpaper.com/paper/2310.12638)

Discussion