PSYCHIC: A Neuro-Symbolic Framework for Knowledge Graph Question-Answering Grounding - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

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

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%.
Fichier principal
Vignette du fichier
ghtpqfzgfmxhbzfdfwzkqsbpygtpbfyx.pdf (736.67 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Licence : CC BY - Attribution

Dates and versions

hal-04311370 , version 1 (28-11-2023)

Licence

Attribution

Identifiers

Cite

Hanna Abi Akl. PSYCHIC: A Neuro-Symbolic Framework for Knowledge Graph Question-Answering Grounding. ISWC 2023 - International semantic web conference, Juanzi Li; Manolis Koubarakis; Valentina Ivanova; Wen Zhang; Dimitris Plexousakis; Vassilis Christophides; Heng Ji; Haofen Wang; Andrea Nuzzolese; Evgeny Kharlamov; Zoi Kaoudi; Gong Cheng; Heiko Paulheim; Cogan Shimizu; Eleni Tsalapati; Ioannis Chrysakis; George Vouros; Ioannis Karatzanis; Lei Hou; Terry R. Payne; Valentina Presutti; Guilin Qi; María Poveda-Villalón; Bo Fu; Giorgos Stoilos; Laura Hollink; Jose Manuel Gomez-Perez; Daniel Garijo; Claudia d’Amato; Jeff Z. Pan; Irini Fundulaki; Kozaki Kouji, Nov 2023, Athens (Greece), Greece. ⟨hal-04311370⟩
47 View
7 Download

Altmetric

Share

Gmail Facebook X LinkedIn More