Elamur Research⌕
☰
home / papers / 2026 / Regression-Tested Compositional Semantics: A Graphical Development Environment for Glue and Description-by-Analysis

Regression-Tested Compositional Semantics: A Graphical Development Environment for Glue and Description-by-Analysis

Summary

The authors address the decline of formal semantic parsing, which they argue still offers more transparency and predictable operator interactions than neural parsers that generalise poorly out of domain. They present a browser-based graphical environment built on XLE+Glue for writing and testing compositional semantic analyses over syntactic parses. These can be LFG analyses from XLE grammars or UD parses produced by Stanza. Users write description-by-analysis (DBA) rewrite rules that attach Glue meaning constructors to syntactic graphs. The system computes the resulting derivations and handles ambiguity with discriminants, borrowed from treebanking practice. Instead of scoring output against gold annotations, analyses are checked through regression testing on natural language inference with a theorem prover. The contribution is the tool and its workflow, not a benchmark score. The authors propose an incremental approach: several interoperable medium-sized grammars, each targeting particular inference patterns, instead of one broad-coverage parser. The aim is to make formal meaning banks easier to build, especially for LFG, which has syntactic treebanks but lacks large meaning banks.

Key points

  • The platform combines three components:
    • LiGER (Linguistic Graph Expansion and Rewriting), which applies DBA rules.
    • The Glue semantics workbench (GSWB), which computes Glue derivations.
    • An interface to the Vampire theorem prover, used for NLI.
  • All annotation layers are stored as interconnected layered graphs, reflecting LFG's projection architecture. These layers include c-structure, f-structure and s-structure.
  • Scope and meaning-constructor discriminants filter ambiguous derivations, following Rosén et al. (2006).
  • The interface has three views:
    • a DBA view showing rules, the annotated graph and the history of applied rules;
    • a semantic composition view;
    • a combined full view.
  • The code is on GitHub at Mmaz1988/xleplusglue, branch dmr2026_regression_testing. Using XLE grammars requires Linux XLE binaries, obtained through the University of Konstanz.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/29smqkidu5sm

@inproceedings{zymla2026regression,
  title = {{Regression-Tested Compositional Semantics: A Graphical Development Environment for Glue and Description-by-Analysis}},
  author = {Zymla, Mark-Matthias and Kruschwitz, Kascha},
  booktitle = {Proceedings of The Seventh International Workshop on Designing Meaning Representations (DMR 2026) @ LREC 2026},
  year = {2026},
  doi = {10.63317/29smqkidu5sm},
  url = {https://doi.org/10.63317/29smqkidu5sm}
}

References

51 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Lasha Abzianidze and Johan Bos. 2019. Thirty musts for meaning banking. In Proceedings of the First International Workshop on Designing Meaning Representations, pages 15–27. Association for Computational Linguistics. find
  2. Lasha Abzianidze, Rik Van Noord, Chunliu Wang, and Johan Bos. 2020. The parallel meaning bank: A framework for semantically annotating multiple languages. Applied Mathematics and Informatics, 25(2):45–60. find our card
  3. Avery D Andrews. 2008. The role of PRED in LFG + Glue. In Proceedings of the LFG’08 Conference, pages 47–67, Stanford, CA. CSLI Publications. find
  4. Ash Asudeh. 2006. Direct compositionality and the architecture of lfg. Intelligent linguistic architectures: Variations on themes by Ronald M. Kaplan, pages 363–387. find
  5. Ash Asudeh. 2023. Glue semantics. In Handbook of Lexical Functional Grammar, pages 651–697. Language Science Press, Berlin. find
  6. Daniel G. Bobrow, Bob Cheslow, Cleo Condoravdi, Lauri Karttunen, Tracy Holloway King, Rowan Nairn, Valeria de Paiva, Charlotte Price, and Annie Zaenen. 2007. PARC’s Bridge and Question Answering System. In Proceedings of the GEAF 2007 Workshop, pages 1–22. find
  7. Julia Bonn, Matthew J. Buchholz, Jayeol Chun, Andrew Cowell, William Croft, Lukas Denk, Sijia Ge, Jan Hajič, Kenneth Lai, James H. Martin, Skatje Myers, Alexis Palmer, Martha Palmer, Claire Benet Post, James Pustejovsky, Kristine Stenzel, Haibo Sun, Zdeňka Urešová, Rosa Vallejos, Jens E. L. Van Gy… find
  8. Johan Bos. 2009. Applying automated deduction to natural language understanding. Journal of Applied Logic, 7(1):100–112. find
  9. Joan Bresnan, Ash Asudeh, Ida Toivonen, and Stephen Wechsler. 2015. Lexical-functional syntax, volume 16. John Wiley & Sons. find
  10. Harry Bunt. 2008. Semantic underspecification: which technique for what purpose? In Computing Meaning, pages 55–85. Springer. find
  11. Harry Bunt. 2015. On the principles of semantic annotation. In Proceedings of the 11th Joint ACL-ISO Workshop on Interoperable Semantic Annotation (ISA-11). find
  12. Miriam Butt, Tina Bögel, Mark-Matthias Zymla, and Benazir Mumtaz. 2024. Alternative questions in urdu: from the speech signal to semantics. In Proceedings of the LFG’24 Conference, Konstanz. PubliKon. find
  13. Miriam Butt, Tracy Holloway King, María-Eugenia Niño, and Frédérique Segond. 1999. A grammar writer’s cookbook. CSLI Publications. find
  14. Nikos Chatzichrisafis, Dick Crouch, Tracy Holloway King, Rowan Nairn, Manny Rayner, and Marianne Santaholma. 2007. Regression testing for grammar-based systems. In Proceedings of the GEAF07 Workshop, pages 128–143, Stanford, CA. CSLI Publications. find
  15. Dick Crouch, Mary Dalrymple, Ronald M. Kaplan, Tracy Holloway King, John T. Maxwell III, and Paula Newman. 2017. XLE documentation. Palo Alto Research Center. find
  16. Richard Crouch. 2005. Packed rewriting for mapping semantics to KR. In Proceedings of the Sixth International Workshop on Computational Semantics (IWCS-6), pages 103–114, Tilburg. find
  17. Richard Crouch and Tracy Holloway King. 2006. Semantics via f-structure rewriting. In Proceedings of the LFG’06 Conference, pages 145–165, Stanford, CA. CSLI Publications. find
  18. Mary Dalrymple. 1999. Semantics and syntax in Lexical Functional Grammar: The resource logic approach. The MIT Press, Cambridge, MA. find
  19. Mary Dalrymple. 2001. Lexical Functional Grammar. Number 34 in Syntax and Semantics. Academic Press, San Diego, CA. find
  20. Mary Dalrymple, editor. 2023. Handbook of Lexical Functional Grammar . Number 13 in Empirically Oriented Theoretical Morphology and Syntax. Language Science Press, Berlin. find
  21. Mary Dalrymple, John Lamping, Fernando Pereira, and Vijay Saraswat. 1999. Quantification, anaphora, and intensionality. In Mary Dalrymple, editor, Semantics and syntax in Lexical Functional Grammar: the resource logic approach, pages 39–89. find
  22. Mary Dalrymple, Agnieszka Patejuk, and Mark-Matthias Zymla. 2020. XLE+Glue – a new tool for integrating semantic analysis in XLE. In Proceedings of the LFG’20 Conference, pages 89– 108, Stanford, CA. CSLI Publications. find
  23. Jamie Y Findlay, Saeedeh Salimifar, Ahmet Yıldırım, and Dag TT Haug. 2023. Rule-based semantic interpretation for Universal Dependencies. In Proceedings of the Sixth Workshop on Universal Dependencies (UDW, GURT/SyntaxFest 2023), pages 47–57. find
  24. Dan Flickinger, Yi Zhang, and Valia Kordoni. 2012. Deepbank. a dynamically annotated treebank of the wall street journal. In Proceedings of the 11th International Workshop on Treebanks and Linguistic Theories, pages 85–96. find
  25. Hayate Funakura, Hyunsoo Kim, and Koji Mineshima. 2025. A theorem-proving-based evaluation of neural semantic parsing. In Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 295–306. find
  26. Izumi Haruta, Koji Mineshima, and Daisuke Bekki. 2022. Implementing natural language inference for comparatives. Journal of Language Modelling, 10(1). find
  27. Dag Haug, Jamie Yates Findlay, and Ahmet Yıldırım. 2023. The long and the short of it: DRASTIC, a semantically annotated dataset containing sentences of more natural length. In Proceedings of the Fourth International Workshop on Designing Meaning Representations, pages 89–98. find
  28. Luheng He, Julian Michael, Mike Lewis, and Luke Zettlemoyer. 2016. Human-in-the-loop parsing. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2337–2342, Austin, Texas. Association for Computational Linguistics. find
  29. Nancy Ide and Harry Bunt. 2010. Anatomy of Annotation Schemes: Mapping to GrAF. In Proceedings of the Fourth Linguistic Annotation Workshop, pages 247–255. toolkit for exploring linear logic and Glue semantics. In Proceedings of the LFG’18 Conference, pages 249–263, Stanford, CA. CSLI Publications. find
  30. Kevin Knight, Bianca Badarau, Laura Baranescu, Claire Bonial, Madalina Bardocz, Kira Griffitt, Ulf Hermjakob, Daniel Marcu, Martha Palmer, Tim O’Gorman, and Nathan Schneider. 2020. Abstract meaning representation (amr) annotation release 3.0. LDC2020T02, Web Download. DOI: 10.35111/44cy-bp51. — [doi:10.35111/44cy-bp51](https://doi.org/10.35111/44cy-bp51) find
  31. Adam Przepiórkowski and Agnieszka Patejuk. 2023. Filling gaps with Glue. In Proceedings of the LFG’23 Conference, pages 223–240, Konstanz. PubliKon. find
  32. Laura Kovács and Andrei Voronkov. 2013. First-order theorem proving and vampire. In International Conference on Computer Aided Verification, pages 1–35. Springer. find
  33. Iddo Lev. 2007. Packed computation of exact meaning representations. Ph.D. thesis, Stanford University. find
  34. Zhongli Li, Qingyu Zhou, Chao Li, Ke Xu, and Yunbo Cao. 2021. Improving BERT with syntax-aware local attention. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 645–653, Online. Association for Computational Linguistics. find
  35. Matthias Lindemann, Alexander Koller, and Ivan Titov. 2024. Strengthening structural inductive biases by pre-training to perform syntactic transformations. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 11558–11573, Miami, Florida, USA. Assoc… find
  36. Shixia Liu, Xiting Wang, Mengchen Liu, and Jun Zhu. 2017. Towards Better Analysis of Machine Learning Models: A Visual Analytics Perspective. Visual Informatics, 1(1):48–56. Publisher: Elsevier. find
  37. Bill MacCartney and Christopher D. Manning. 2009. An extended model of natural logic. In Proceedings of the eight International Conference on Computational Semantics, pages 140–156. find
  38. Christopher D. Manning. 2006. Local Textual Inference: It’s Hard to Circumscribe, but You Know It When You See It — and NLP Needs It. Manuscript, Stanford University. find
  39. Mitchell P. Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19(2):313–330. find our card
  40. Moritz Meßmer and Mark-Matthias Zymla. 2018. The Glue semantics workbench: a modular Stephen Guy Pulman. 2018. Second order inference in natural language semantics. Journal of Language Modelling, 6(1):1–40. find
  41. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D Manning. 2020. Stanza: A python natural language processing toolkit for many human languages. In Proceedings of the 58th annual meeting of the association for computational linguistics: system demonstrations, pages 101–108. find our card
  42. Victoria Rosén, Koenraad De Smedt, and Paul Meurer. 2006. Towards a toolkit linking treebanking to grammar development. In Proceedings of the Fifth Workshop on Treebanks and Linguistic Theories, pages 55–66. find
  43. Pontus Stenetorp, Sampo Pyysalo, Goran Topić, Tomoko Ohta, Sophia Ananiadou, and Jun’ichi Tsujii. 2012. Brat: a web-based tool for nlp-assisted text annotation. In Proceedings of the Demonstrations at the 13th Conference of the European Chapter of the Association for Computational Linguistics, page… find our card
  44. Emma Strubell, Patrick Verga, Daniel Andor, David Weiss, and Andrew McCallum. 2018. Linguistically-informed self-attention for semantic role labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 5027–5038, Brussels, Belgium. Association for Comput… find our card
  45. Sebastian Sulger, Miriam Butt, Tracy Holloway King, Paul Meurer, Tibor Laczkó, György Rákosi, Cheikh M Bamba Dione, Helge Dyvik, Victoria Rosén, Koenraad De Smedt, Agnieszka Patejuk, Özlem Çetinŏglu, I Wayan Arka, and Meladel Mistica. 2013. ParGramBank: The ParGram Parallel Treebank. In ACL, pages… find
  46. Geoff Sutcliffe, Stephan Schulz, Koen Claessen, and Allen Van Gelder. 2006. Using the TPTP language for writing derivations and finite interpretations. In Automated Reasoning – IJCAR 2006, volume 4130 of Lecture Notes in Computer Science, pages 67–81, Seattle, WA, USA. Springer. find
  47. Shuai Zhang, Lijie Wang, Xinyan Xiao, and Hua Wu. 2022. Syntax-guided contrastive learning for pre-trained language model. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2430–2440, Dublin, Ireland. Association for Computational Linguistics. find
  48. Xiao Zhang, Gosse Bouma, and Johan Bos. 2025. Neural semantic parsing with extremely rich symbolic meaning representations. Computational Linguistics, 51(1):235–274. find
  49. Mark-Matthias Zymla. 2024. Tense and aspect in multilingual semantic construction. Ph.D. thesis, University of Konstanz. find
  50. Mark-Matthias Zymla, Mary Dalrymple, and Agnieszka Patejuk. 2025a. Computational semantic tools for Glue semantics. In Proceedings of the 16th International Conference on Computational Semantics (IWCS 2025), pages 189–207, Düsseldorf. Association for Computational Linguistics. find
  51. Mark-Matthias Zymla, Kascha Kruschwitz, and Paul Zodl. 2025b. An instructive implementation of semantic parsing and reasoning using lexical functional grammar. In Proceedings of the 2nd Bridging the Gap between Human and Automated Reasoning Workshop (BriGap-2). find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zymla-2026-regression-tested-compositional-semantics-graphical/