Exploiting Task Reversibility of DRS Parsing and Generation: Challenges and Insights from a Multi-lingual Perspective

Muhammad Saad Amin, Luca Anselma, Alessandro Mazzei


Abstract
Semantic parsing and text generation exhibit reversible properties when utilizing Discourse Representation Structures (DRS). However, both processes—text-to-DRS parsing and DRS-to-text generation—are susceptible to errors. In this paper, we exploit the reversible nature of DRS to explore both error propagation, which is commonly seen in pipeline methods, and the less frequently studied potential for error correction. We investigate two pipeline approaches: Parse-Generate-Parse (PGP) and Generate-Parse-Generate (GPG), utilizing pre-trained language models where the output of one model becomes the input for the next. Our evaluation uses the Parallel Meaning Bank dataset, focusing on Urdu as a low-resource language, Italian as a mid-resource language, and English serving as a high-resource baseline. Our analysis highlights that while pipelines are theoretically suited for error correction, they more often propagate errors, with Urdu exhibiting the greatest sensitivity, Italian showing a moderate effect, and English demonstrating the highest stability. This variation highlights the unique challenges faced by low-resource languages in semantic processing tasks. Further, our findings suggest that these pipeline methods support the development of more linguistically balanced datasets, enabling a comprehensive assessment across factors like sentence structure, length, type, polarity, and voice. Our cross-linguistic analysis provides valuable insights into the behavior of DRS processing in low-resource contexts, demonstrating both the potential and limitations of reversible pipeline approaches.
Anthology ID:
2025.loreslm-1.22
Volume:
Proceedings of the First Workshop on Language Models for Low-Resource Languages
Month:
January
Year:
2025
Address:
Abu Dhabi, United Arab Emirates
Editors:
Hansi Hettiarachchi, Tharindu Ranasinghe, Paul Rayson, Ruslan Mitkov, Mohamed Gaber, Damith Premasiri, Fiona Anting Tan, Lasitha Uyangodage
Venues:
LoResLM | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
268–286
Language:
URL:
https://aclanthology.org/2025.loreslm-1.22/
DOI:
Bibkey:
Cite (ACL):
Muhammad Saad Amin, Luca Anselma, and Alessandro Mazzei. 2025. Exploiting Task Reversibility of DRS Parsing and Generation: Challenges and Insights from a Multi-lingual Perspective. In Proceedings of the First Workshop on Language Models for Low-Resource Languages, pages 268–286, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Exploiting Task Reversibility of DRS Parsing and Generation: Challenges and Insights from a Multi-lingual Perspective (Amin et al., LoResLM 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.loreslm-1.22.pdf