---
title: "Modelling Idiomatic Expressions in Abstract — Gareeva 2026"
description: "AMR parsers tend to struggle with idioms because these expressions can carry either a literal or a figurative sense depending on context, and AMR…"
authors: ["Venera Gareeva", "Johannes Heinecke"]
year: 2026
venue: "Proceedings of The Seventh International Workshop on Designing Meaning Representations (DMR 2026) @ LREC 2026"
source: "https://aclanthology.org/2026.dmr-1.3/"
doi: "10.63317/3hkt3x4zzok9"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/gareeva-2026-modelling-idiomatic-expressions-abstract-meaning/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/gareeva-2026-modelling-idiomatic-expressions-abstract-meaning/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/page/3/) / Modelling Idiomatic Expressions in Abstract Meaning Representation

# Modelling Idiomatic Expressions in Abstract Meaning Representation

**Authors:** Venera Gareeva, [Johannes Heinecke](https://md.research.elamur.ai/free/authors/johannes-heinecke/) · **Year:** 2026 · **Venue:** Proceedings of The Seventh International Workshop on Designing Meaning Representations (DMR 2026) @ LREC 2026 · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.dmr-1.3/) · [PDF](https://aclanthology.org/2026.dmr-1.3.pdf) · [DOI 10.63317/3hkt3x4zzok9](https://doi.org/10.63317/3hkt3x4zzok9) · [OpenAlex](https://openalex.org/W7166524596)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14)

## Summary
AMR parsers tend to struggle with idioms because these expressions can carry either a literal or a figurative sense depending on context, and AMR training data contains few of them. A survey of AMR 3.0 with the metAMoRphosED editor found that idioms are rare and handled inconsistently. Some map to PropBank frames, some are rewritten as equivalent concepts, and many are left literal or missing. To fill this gap, the authors built an English corpus of potentially idiomatic expressions (PIEs) paired with AMR graphs. It draws on a hand-picked subset of MAGPIE, plus LLM-generated sentences that add more literal uses. Figurative uses are annotated with an existing PropBank idiom frame where one exists, or otherwise with a paraphrase concept. A rule-based script swaps the corresponding subgraphs, while literal uses keep their compositional structure. A Flan-T5-based AMR parser trained on AMR 3.0 was then fine-tuned on this corpus. The baseline parser mostly produced literal readings, and fine-tuning brought its graphs closer to the intended interpretation. This makes the work a step toward context-sensitive semantic parsing of figurative language.

## Key points
- The corpus covers 41 mostly verbal idioms, each attested in both literal and idiomatic contexts. It has 3,582 sentences, split into 2,886 train, 360 dev, and 336 test. The sources are 3,352 MAGPIE sentences and 250 literal-focused sentences generated with GPT-4.1-nano via one-shot prompting; the reported counts do not sum exactly to the final total.
- Annotation follows two rules. If PropBank already has a frame for the idiom (e.g., follow-suit-06, steer-clear-02, change-hands-06), that frame is used. Otherwise the figurative meaning is paraphrased, so "tie the knot" becomes marry-01 and "bear fruit" becomes produce-01.
- A single annotator labelled the corpus, so no inter-annotator agreement is reported.
- The parser is Flan-T5 (base and large were compared; base was selected) trained on AMR 3.0 (LDC2020T02, about 60k sentences). Evaluation uses Smatch-style graph-overlap metrics.
- English was chosen because AMR relies on PropBank and multilingual PropBanks have low coverage, such as Universal Propositions with 533 French verbs. The authors argue that simply translating the corpus would not preserve idiom equivalence across languages.

*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](https://md.research.elamur.ai/free/shelves/linguistics/) · [Machine translation](https://md.research.elamur.ai/free/shelves/machine-translation/)

Topics: [Semantic role labeling](https://md.research.elamur.ai/free/topics/semantic-role-labeling/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{gareeva2026modelling,
  title = {{Modelling Idiomatic Expressions in Abstract Meaning Representation}},
  author = {Gareeva, Venera and Heinecke, Johannes},
  booktitle = {Proceedings of The Seventh International Workshop on Designing Meaning Representations (DMR 2026) @ LREC 2026},
  year = {2026},
  doi = {10.63317/3hkt3x4zzok9},
  url = {https://doi.org/10.63317/3hkt3x4zzok9}
}
```

- [← previous Modeling the Memory-Surprisal Trade-Off over Time: Communicative Efficiency Decreases with Lexico-Grammatical Change in Scientific English](https://md.research.elamur.ai/free/papers/steuer-2026-modeling-memory-surprisal-trade-off/)
- [next → Modelling the Morphology of Verbal Paradigms: A Case Study in the Tokenization of Turkish and Hebrew](https://md.research.elamur.ai/free/papers/aclbulk-2026-samo-modelling-morphology-verbal-paradigms-case/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/page/3/)

## References

23 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Alan Akbik, Laura Chiticariu, Marina Danilevsky, Yunyao Li, Shivakumar Vaithyanathan, and Huaiyu Zhu. 2015. Generating high quality proposition Banks for multilingual semantic role labeling. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 397–407, Beijing, China. Association for Computational Linguistics. [↗](https://doi.org/10.3115/v1/p15-1039) [our card](https://md.research.elamur.ai/free/papers/akbik-2015-generating-high-quality-proposition-banks/)
2. Timothy Baldwin and Su Nam Kim. 2010. Multiword expressions. In Handbook of Natural Language Processing. [find](https://scholar.google.com/scholar?q=Timothy+Baldwin+and+Su+Nam+Kim%2E+2010%2E+Multiword+expressions%2E+In+Handbook+of+Natural+Language+Processing%2E)
3. Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider. 2013. Abstract Meaning Representation for Sembanking. In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, pages 178–186, Sofia, Bulgaria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Laura+Banarescu%2C+Claire+Bonial%2C+Shu+Cai%2C+Madalina+Georgescu%2C+Kira+Griffitt%2C+Ulf+Hermjakob%2C+Kevin+Knight%2C+Philipp+Koehn%2C+Martha+Palmer%2C+and+Nathan+Schneider%2E+2013%2E+Abstract+Meaning+Representation+for+S) [our card](https://md.research.elamur.ai/free/papers/banarescu-2013-abstract-meaning-representation-sembanking/)
4. Sara Beck and Andrea Weber. 2020. Context and literality in idiom processing: Evidence from self-paced reading. Journal of Psycholinguistic Research, 49. [↗](https://doi.org/10.1007/s10936-020-09719-2)
5. Shu Cai and Kevin Knight. 2013. Smatch: an evaluation metric for semantic feature structures. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 748–752, Sofia, Bulgaria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Shu+Cai+and+Kevin+Knight%2E+2013%2E+Smatch%3A+an+evaluation+metric+for+semantic+feature+structures%2E+In+Proceedings+of+the+51st+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+2%3A+Shor)
6. Dang Chung. 2024. Challenges of translating idiomatic expressions: A cross-linguistic analysis at a university in hanoi, vietnam. International Journal of Social Science and Human Research, 07. [↗](https://doi.org/10.47191/ijsshr/v7-i10-39)
7. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Alex Castro-Ros, Marie Pellat, Kevin Robinson, Dasha Valter, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, Andrew Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V. Le, and Jason Wei. 2022. Scaling instruction-finetuned language models. [↗](https://doi.org/10.48550/arxiv.2210.11416)
8. Kilian Evang, Rafael Ehren, and Laura Kallmeyer. 2025. The proper treatment of verbal idioms in German discourse representation structure parsing. In Proceedings of the 16th International Conference on Computational Semantics, pages 156–165, Düsseldorf, Germany. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Kilian+Evang%2C+Rafael+Ehren%2C+and+Laura+Kallmeyer%2E+2025%2E+The+proper+treatment+of+verbal+idioms+in+German+discourse+representation+structure+parsing%2E+In+Proceedings+of+the+16th+International+Conference+o)
9. Hessel Haagsma, Johan Bos, and Malvina Nissim. 2020. MAGPIE: A large corpus of potentially idiomatic expressions. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 279–287, Marseille, France. European Language Resources Association. [find](https://scholar.google.com/scholar?q=Hessel+Haagsma%2C+Johan+Bos%2C+and+Malvina+Nissim%2E+2020%2E+MAGPIE%3A+A+large+corpus+of+potentially+idiomatic+expressions%2E+In+Proceedings+of+the+Twelfth+Language+Resources+and+Evaluation+Conference%2C+pages+279%E2%80%93) [our card](https://md.research.elamur.ai/free/papers/haagsma-2020-magpie-large-corpus-potentially-idiomatic/)
10. Wei He, Marco Idiart, Carolina Scarton, and Aline Villavicencio. 2024. Enhancing idiomatic representation in multiple languages via an adaptive contrastive triplet loss. In Findings of the Association for Computational Linguistics: ACL 2024, pages 12473–12485, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Wei+He%2C+Marco+Idiart%2C+Carolina+Scarton%2C+and+Aline+Villavicencio%2E+2024%2E+Enhancing+idiomatic+representation+in+multiple+languages+via+an+adaptive+contrastive+triplet+loss%2E+In+Findings+of+the+Association)
11. Johannes Heinecke. 2023. metAMoRphosED, a graphical editor for Abstract Meaning Representation. In Proceedings of the 19th Joint ACL-ISO Workshop on Interoperable Semantics (ISA-19), pages 27–32, Nancy, France. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Johannes+Heinecke%2E+2023%2E+metAMoRphosED%2C+a+graphical+editor+for+Abstract+Meaning+Representation%2E+In+Proceedings+of+the+19th+Joint+ACL%2DISO+Workshop+on+Interoperable+Semantics+%28ISA%2D19%29%2C+pages+27%E2%80%9332%2C+Nanc)
12. Robert T. Kasper. 1989. A flexible interface for linking applications to Penman’s sentence generator. In Speech and Natural Language: Proceedings of a Workshop Held at Philadelphia, Pennsylvania, February 21-23, 1989. [↗](https://doi.org/10.3115/100964.100979)
13. Paul Kingsbury and Martha Palmer. 2002. From TreeBank to PropBank. In Proceedings of the Third International Conference on Language Resources and Evaluation, pages 1989–1993, Las Palmas, Canary Islands, Spain. European Language Resources Association. [↗](https://doi.org/10.63317/3gh6v2hd4z55) [our card](https://md.research.elamur.ai/free/papers/kingsbury-2002-treebank-propbank/)
14. Young-Suk Lee, Ramón Fernandez Astudillo, Radu Florian, Tahira Naseem, and Salim Roukos. 2023. Amr parsing with instruction fine-tuned pre-trained language models. [↗](https://doi.org/10.48550/arxiv.2304.12272)
15. Behrooz Mansouri. 2025. Survey of abstract meaning representation: Then, now, future. [↗](https://doi.org/10.48550/arxiv.2505.03229) [our card](https://md.research.elamur.ai/free/papers/mansouri-2025-survey-abstract-meaning-representation-then/)
16. Geoffrey Nunberg, Ivan A. Sag, and Thomas Wasow. 1994. Idioms. Language, 70(3):491–538. [find](https://scholar.google.com/scholar?q=Geoffrey+Nunberg%2C+Ivan+A%2E+Sag%2C+and+Thomas+Wasow%2E+1994%2E+Idioms%2E+Language%2C+70%283%29%3A491%E2%80%93538%2E)
17. Juri Opitz. 2023. SMATCH++: Standardized and extended evaluation of semantic graphs. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1595–1607, Dubrovnik, Croatia. Association for Computational Linguistics. [↗](https://doi.org/10.48448/ggp5-ze79)
18. Juri Opitz, Anette Frank, and Letitia Parcalabescu. 2020. Amr similarity metrics from principles. Transactions of the Association for Computational Linguistics, 8(0):522–538. [↗](https://doi.org/10.1162/tacl_a_00329)
19. Martha Palmer, Daniel Gildea, and Paul Kingsbury. 2005. The Proposition Bank: An Annotated Corpus of Semantic Roles. Computational Linguistics, 31(1):71–106. [↗](https://doi.org/10.1162/0891201053630264) [our card](https://md.research.elamur.ai/free/papers/palmer-2005-proposition-bank-annotated-corpus-semantic/)
20. Carlos Ramisch. 2023. Multiword expressions in computational linguistics. Habilitation à diriger des recherches, Aix Marseille Université (AMU). [find](https://scholar.google.com/scholar?q=Carlos+Ramisch%2E+2023%2E+Multiword+expressions+in+computational+linguistics%2E+Habilitation+%C3%A0+diriger+des+recherches%2C+Aix+Marseille+Universit%C3%A9+%28AMU%29%2E)
21. Agata Savary, Silvio Cordeiro, and Carlos Ramisch. 2019. Without lexicons, multiword expression identification will never fly: A position statement. In Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019), pages 79–91, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Agata+Savary%2C+Silvio+Cordeiro%2C+and+Carlos+Ramisch%2E+2019%2E+Without+lexicons%2C+multiword+expression+identification+will+never+fly%3A+A+position+statement%2E+In+Proceedings+of+the+Joint+Workshop+on+Multiword+E)
22. Ziheng Zeng and Suma Bhat. 2021. Idiomatic expression identification using semantic compatibility. Transactions of the Association for Computational Linguistics, 9:1546–1562. 8. [↗](https://doi.org/10.1162/tacl_a_00442) [our card](https://md.research.elamur.ai/free/papers/zeng-2021-idiomatic-expression-identification-semantic-compatibility/)
23. Language Resource References Kevin Knight and Bianca Badarau and Laura Baranescu and Claire Bonial and Madalina Bardocz and Kira Griffitt and Ulf Hermjakob and Daniel Marcu and Martha Palmer and Tim O’Gorman and Nathan Schneider. 2020. Abstract Meaning Representation (AMR) Annotation Release 3.0. Linguistic Data Consortium. distributed via LDC: LDC2020T02, 3.0, ISLRN 676-697-177-821-8. [find](https://scholar.google.com/scholar?q=Language+Resource+References+Kevin+Knight+and+Bianca+Badarau+and+Laura+Baranescu+and+Claire+Bonial+and+Madalina+Bardocz+and+Kira+Griffitt+and+Ulf+Hermjakob+and+Daniel+Marcu+and+Martha+Palmer+and+Tim+O)