From Graph to Text and Back: Semantic Fidelity in Automated Industrial Knowledge Graphs
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), ACL 2026, San Diego, California, USA
Presented on , 1 citation on Google Scholar
In short
The paper proposes a self-supervised round-trip pipeline that turns knowledge-graph triples into text, rebuilds the graph from that text, and keeps only verbalizations that allow full recovery of the original graph. The round-trip score correlates strongly with expert judgment, and fine-tuning LLMs on the retained data improves both triple extraction and faithful text generation without manual annotation.
Cite
@inproceedings{zeinalipour-etal-2026-graph,
title = "From Graph to Text and Back: Semantic Fidelity in Automated Industrial Knowledge Graphs",
author = "Zeinalipour, Kamyar and
Severini, Silvia and
Borghini, Alessia and
Cardarelli, Sara and
Maggini, Marco and
Gori, Marco",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 6: Industry Track)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.140/",
doi = "10.18653/v1/2026.acl-industry.140",
pages = "2095--2111",
ISBN = "979-8-89176-394-4"
}