Towards Neuro-Symbolic Approaches for Referring Expression Generation

Manar Ali, Marika Sarzotti, Simeon Junker, Hendrik Buschmeier, Sina Zarrieß


Abstract
Referring Expression Generation (REG) has a long-standing tradition in computational linguistics, and often aims to develop cognitively plausible models of language generation and dialogue modeling, in a multimodal context. Traditional approaches to reference have been mostly symbolic, recent ones have been mostly neural. Inspired by the recent interest in neuro-symbolic approaches in both fields – language and vision – we revisit REG from these perspectives. We review relevant neuro-symbolic approaches to language generation on the one hand and vision on the other hand, exploring possible future directions for cognitively plausible models of reference generation/reference game modeling.
Anthology ID:
2025.clasp-main.4
Volume:
Proceedings of the 2025 CLASP Conference on Language models And RePresentations (LARP)
Month:
September
Year:
2025
Address:
Gothenburg, Sweden
Editors:
Nikolai Ilinykh, Mattias Appelgren, Erik Lagerstedt
Venues:
CLASP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
38–50
Language:
URL:
https://aclanthology.org/2025.clasp-main.4/
DOI:
Bibkey:
Cite (ACL):
Manar Ali, Marika Sarzotti, Simeon Junker, Hendrik Buschmeier, and Sina Zarrieß. 2025. Towards Neuro-Symbolic Approaches for Referring Expression Generation. In Proceedings of the 2025 CLASP Conference on Language models And RePresentations (LARP), pages 38–50, Gothenburg, Sweden. Association for Computational Linguistics.
Cite (Informal):
Towards Neuro-Symbolic Approaches for Referring Expression Generation (Ali et al., CLASP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.clasp-main.4.pdf