Browse by author
Lookup NU author(s): Ollie Fox, Dr Giacomo BergamiORCiD, Professor Graham MorganORCiD
This is the authors' accepted manuscript of a conference proceedings (inc. abstract) that has been published in its final definitive form by Springer Verlag, 2024.
For re-use rights please refer to the publisher's terms and conditions.
This paper proposes LaSSI, a Natural Language Processing (NLP) pipeline contextualising verified Artificial Intelligence (AI) by transforming text via Montague Grammars (MGs). We are approaching from the point-of-view of graphs and logic, in which we achieve explainable sentence similarity in terms of Knowledge Base (KB) expansion and possible worlds semantics. Experiments in the present paper excel current state-of-the-art, Graph Retrieval-Augmented Generation (RAG)-based technologies, through a novel method surpassing vector-based and graph-based sentence similarity metrics.
Author(s): Fox OR, Bergami G, Morgan G
Editor(s): Chbeir, R; Ilarri, S; Manolopoulos, Y; Revesz, PZ; Bernardino, J; Leung, CK
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: The 28th International Database Engineered Applications Symposium
Year of Conference: 2024
Online publication date: 28/08/2018
Acceptance date: 30/07/2024
Date deposited: 04/10/2024
Publisher: Springer Verlag
URL: https://conferences.sigappfr.org/ideas2024/program/#session_3
ePrints DOI: 10.57711/10pf-9423
Data Access Statement: This is the post-revision paper and before copyrighting.
