---
title: "Metaphor Identification in Spanish Oncological Discourse: The"
description: "Automatic metaphor detection performs well on large general-domain English benchmarks such as the VUA corpus. 0.49 F1. 22 references."
authors: ["Lucia Pitarch", "Jordi Bernad", "Gemma Bel-Enguix"]
year: 2026
venue: "Proceedings of Learning Non-Literal Expressions with Small Data @ LREC 2026"
source: "https://aclanthology.org/2026.nonliteral-1.4/"
doi: "10.63317/2hvq7fqourt3"
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/en/papers/pitarch-2026-metaphor-identification-spanish-oncological-discourse/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/pitarch-2026-metaphor-identification-spanish-oncological-discourse/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/41/) / Metaphor Identification in Spanish Oncological Discourse: The Role of Explicit Meaning in Low-Resource Settings

# Metaphor Identification in Spanish Oncological Discourse: The Role of Explicit Meaning in Low-Resource Settings

**Authors:** [Lucia Pitarch](https://md.research.elamur.ai/free/en/authors/lucia-pitarch/), Jordi Bernad and [Gemma Bel-Enguix](https://md.research.elamur.ai/free/en/authors/gemma-bel-enguix/) · **Year:** 2026 · **Venue:** [Proceedings of Learning Non-Literal Expressions with Small Data @ LREC 2026](https://md.research.elamur.ai/free/en/venues/nonliteral/) ([Learning Non-Literal Expressions with Small Data @ LREC 2026](https://md.research.elamur.ai/free/en/venues/nonliteral/2026/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **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.nonliteral-1.4/) · [PDF](https://aclanthology.org/2026.nonliteral-1.4.pdf) · [DOI 10.63317/2hvq7fqourt3](https://doi.org/10.63317/2hvq7fqourt3) · [OpenAlex](https://openalex.org/W7166534677)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Automatic metaphor detection performs well on large general-domain English benchmarks such as the VUA corpus. It transfers poorly, however, to specialized settings with little labeled data, such as Spanish texts about cancer. The authors ask whether explicit meaning information, the core of the Metaphor Identification Procedure (MIP), helps a model in this situation. They use a filtered portion of FLAVORS-AECC, a Spanish oncological dataset where every instance is labeled with WordNet synsets for both its basic meaning (BM) and its meaning in context (CM). On this data they fine-tune the Contrast-WSD architecture with an XLM-RoBERTa-base encoder. They compare three input variants:
- no meaning information (control),
- manually chosen BM,
- the first WordNet sense as BM.

Each variant is tested on a random split and on a split where train and test share no lemmas.

Adding definitions raises F1 sharply, from below 0.30 for the control to above 0.50 in the best configurations. Unexpectedly, hand-curated BM is not reliably better than the first dictionary sense. The authors suspect that longer definitions add noise. Models do best on high-agreement items and worst on verbs. The study supports linguistically informed modeling for low-resource domains.

## Key points
- **Data:** 5,239 single-word instances (verbs, nouns and adjectives only).
  - 18% are marked metaphorical by at least one annotator.
  - POS distribution: 64% verbs, 24% nouns, 12% adjectives.
  - Inter-annotator agreement in the original dataset: 0.49 F1.
- **Setup:** Contrast-WSD with XLM-RoBERTa-base.
  - The Lesk algorithm replaces an external WSD model.
  - Definitions are in Spanish where available, otherwise in English.
  - Best hyperparameters: class weight 5, learning rate 1e-5, batch size 16, 10 epochs.
  - Results are the mean of 5 seeds with 95% confidence intervals.
- **Lemma-based split (F1):**
  - Control: about 0.27–0.29.
  - Manual BM: about 0.34–0.36.
  - First dictionary entry: about 0.36–0.38.
- **Random split (F1):**
  - First dictionary entry: about 0.50.
  - Manual BM: 0.50–0.51 (best reported: 0.514).
  - The gap between the two BM strategies is negligible.
- **Error patterns:** accuracy is higher on instances with strong annotator agreement, and verbs remain the hardest part of speech.

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

## Institutions

- [Universidad Nacional Autónoma de México](https://md.research.elamur.ai/free/en/universities/universidad-nacional-autonoma-de-mexico/) — University, Mexico City, Mexico · 8 works · 288 citations
- [Universidad de Zaragoza](https://md.research.elamur.ai/free/en/universities/universidad-de-zaragoza/) — University, Zaragoza, Spain · 6 works · 5 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 930 works

🧭 Topics (3): [🧵 Discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) · 471 works · [🧷 Idioms & multiword expressions](https://md.research.elamur.ai/free/en/topics/multiword-expressions/) · 222 works · [🌱 Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) · 287 works

## Cite

Cite as: Lucia Pitarch, Jordi Bernad and Gemma Bel-Enguix. 2026. Metaphor Identification in Spanish Oncological Discourse: The Role of Explicit Meaning in Low-Resource Settings. Proceedings of Learning Non-Literal Expressions with Small Data @ LREC 2026.

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

```bibtex
@inproceedings{pitarch2026metaphor,
  title = {{Metaphor Identification in Spanish Oncological Discourse: The Role of Explicit Meaning in Low-Resource Settings}},
  author = {Lucia Pitarch, Jordi Bernad and Gemma Bel-Enguix},
  booktitle = {Proceedings of Learning Non-Literal Expressions with Small Data @ LREC 2026},
  year = {2026},
  doi = {10.63317/2hvq7fqourt3},
  url = {https://doi.org/10.63317/2hvq7fqourt3}
}
```

- [← previous MetaMiners at SMM4H-HeaRD 2026: A Semantic-Structural Knowledge-Enriched Ensemble for SARS-CoV-2 Metadata Identification](https://md.research.elamur.ai/free/en/papers/ursu-2026-metaminers-smm4h-heard-2026-semantic/)
- [next → Methods, Data, and Conceptual Change: Reflections from Two Quantitative Diachronic Case Studies](https://md.research.elamur.ai/free/en/papers/wong-2026-methods-data-conceptual-change-reflections/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/41/)

## References

22 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Tina Krennmayr and Gerard Steen. 2017. VU Amsterdam Metaphor Corpus, pages 1053–1071. Springer Netherlands, Dordrecht. [find](https://scholar.google.com/scholar?q=Tina+Krennmayr+and+Gerard+Steen%2E+2017%2E+VU+Amsterdam+Metaphor+Corpus%2C+pages+1053%E2%80%931071%2E+Springer+Netherlands%2C+Dordrecht%2E)
2. Mateusz Babieno, Masashi Takeshita, Dusan Radisavljevic, Rafal Rzepka, and Kenji Araki. 2022. Miss roberta wilde: Metaphor identification using masked language model with wiktionary lexical definitions. Applied Sciences, 12(4). [find](https://scholar.google.com/scholar?q=Mateusz+Babieno%2C+Masashi+Takeshita%2C+Dusan+Radisavljevic%2C+Rafal+Rzepka%2C+and+Kenji+Araki%2E+2022%2E+Miss+roberta+wilde%3A+Metaphor+identification+using+masked+language+model+with+wiktionary+lexical+definition)
3. George Lakoff and Mark Johnson. 1980. Metaphors We Live By. The University of Chicago Press. [find](https://scholar.google.com/scholar?q=George+Lakoff+and+Mark+Johnson%2E+1980%2E+Metaphors+We+Live+By%2E+The+University+of+Chicago+Press%2E)
4. Mayla Boguslav and Kevin Bretonnel Cohen. 2017. Inter-annotator agreement and the upper limit on machine performance: evidence from biomedical natural language processing. In MEDINFO 2017: Precision Healthcare through Informatics, pages 298–302. IOS Press. [find](https://scholar.google.com/scholar?q=Mayla+Boguslav+and+Kevin+Bretonnel+Cohen%2E+2017%2E+Inter%2Dannotator+agreement+and+the+upper+limit+on+machine+performance%3A+evidence+from+biomedical+natural+language+processing%2E+In+MEDINFO+2017%3A+Precision+H)
5. Michael Lesk. 1986. Automatic sense disambiguation using machine readable dictionaries: how to tell a pine cone from an ice cream cone. In Proceedings of the 5th Annual International Conference on Systems Documentation, SIGDOC ’86, page 24–26, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Michael+Lesk%2E+1986%2E+Automatic+sense+disambiguation+using+machine+readable+dictionaries%3A+how+to+tell+a+pine+cone+from+an+ice+cream+cone%2E+In+Proceedings+of+the+5th+Annual+International+Conference+on+Sys)
6. Lynne Cameron. 2007. The affective discourse dynamics of metaphor clustering. Ilha do Desterro A Journal of English Language, Literatures in English and Cultural Studies, (53):041–062. [find](https://scholar.google.com/scholar?q=Lynne+Cameron%2E+2007%2E+The+affective+discourse+dynamics+of+metaphor+clustering%2E+Ilha+do+Desterro+A+Journal+of+English+Language%2C+Literatures+in+English+and+Cultural+Studies%2C+%2853%29%3A041%E2%80%93062%2E)
7. Yucheng Li, Shun Wang, Chenghua Lin, and Frank Guerin. 2023. Metaphor detection via explicit basic meanings modelling. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 91–100, Toronto, Canada. Association for Computational Lin… [find](https://scholar.google.com/scholar?q=Yucheng+Li%2C+Shun+Wang%2C+Chenghua+Lin%2C+and+Frank+Guerin%2E+2023%2E+Metaphor+detection+via+explicit+basic+meanings+modelling%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+for+Computational+Li)
8. Minjin Choi, Sunkyung Lee, Eunseong Choi, Heesoo Park, Junhyuk Lee, Dongwon Lee, and Jongwuk Lee. 2021. MelBERT: Metaphor detection via contextualized late interaction using metaphorical identification theories. In Proceedings of the 2021 Conference of the North American Chapter of the Association f… [find](https://scholar.google.com/scholar?q=Minjin+Choi%2C+Sunkyung+Lee%2C+Eunseong+Choi%2C+Heesoo+Park%2C+Junhyuk+Lee%2C+Dongwon+Lee%2C+and+Jongwuk+Lee%2E+2021%2E+MelBERT%3A+Metaphor+detection+via+contextualized+late+interaction+using+metaphorical+identificatio)
9. Yufeng Liu, Elena Semino, Judith Rietjens, and Sheila Payne. 2024. Cancer experience in metaphors: patients, carers, professionals, students – a scoping review. BMJ Supportive & Palliative Care, 14(e3):e2366–e2376. [find](https://scholar.google.com/scholar?q=Yufeng+Liu%2C+Elena+Semino%2C+Judith+Rietjens%2C+and+Sheila+Payne%2E+2024%2E+Cancer+experience+in+metaphors%3A+patients%2C+carers%2C+professionals%2C+students+%E2%80%93+a+scoping+review%2E+BMJ+Supportive+%26+Palliative+Care%2C+14%28e3)
10. Rowan Hall Maudslay and Simone Teufel. 2022. Metaphorical polysemy detection: Conventional metaphor meets word sense disambiguation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 65–77. [find](https://scholar.google.com/scholar?q=Rowan+Hall+Maudslay+and+Simone+Teufel%2E+2022%2E+Metaphorical+polysemy+detection%3A+Conventional+metaphor+meets+word+sense+disambiguation%2E+In+Proceedings+of+the+29th+International+Conference+on+Computationa)
11. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2019. [Unsupervised cross-lingual representation learning at scale](https://md.research.elamur.ai/free/en/papers/conneau-2020-unsupervised-cross-lingual-representation-learning/). CoRR, abs/1911.02116.
12. Diana McCarthy, Rob Koeling, Julie Weeds, and John Carroll. 2007. Unsupervised acquisition of predominant word senses. Computational Linguistics, 33(4):553–590. [find](https://scholar.google.com/scholar?q=Diana+McCarthy%2C+Rob+Koeling%2C+Julie+Weeds%2C+and+John+Carroll%2E+2007%2E+Unsupervised+acquisition+of+predominant+word+senses%2E+Computational+Linguistics%2C+33%284%29%3A553%E2%80%93590%2E)
13. Laurence De Backer, Renata Enghels, and Patrick Goethals. 2023. Metaphor analysis meets lexical strings: finetuning the metaphor identification procedure for quantitative semantic analyses. Frontiers in Psychology, 14:1214699. [find](https://scholar.google.com/scholar?q=Laurence+De+Backer%2C+Renata+Enghels%2C+and+Patrick+Goethals%2E+2023%2E+Metaphor+analysis+meets+lexical+strings%3A+finetuning+the+metaphor+identification+procedure+for+quantitative+semantic+analyses%2E+Frontiers+)
14. Lucía Pitarch and Gemma Bel-Enguix. 2026. Modeling metaphor evolution on cancer online narratives. In Proceedings of the 16th International Conference on the Evolution of Language (EVOLANG XVI). [find](https://scholar.google.com/scholar?q=Luc%C3%ADa+Pitarch+and+Gemma+Bel%2DEnguix%2E+2026%2E+Modeling+metaphor+evolution+on+cancer+online+narratives%2E+In+Proceedings+of+the+16th+International+Conference+on+the+Evolution+of+Language+%28EVOLANG+XVI%29%2E)
15. Stefanie Dipper, Adam Roussel, Alexandra Wiemann, Won Kim, and Tra-My Nguyen. 2024. Guidelines for the annotation of deliberate linguistic metaphor. In Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024), pages 53–58, Mexico City, Mexico (Hybrid). Association for Computa… [find](https://scholar.google.com/scholar?q=Stefanie+Dipper%2C+Adam+Roussel%2C+Alexandra+Wiemann%2C+Won+Kim%2C+and+Tra%2DMy+Nguyen%2E+2024%2E+Guidelines+for+the+annotation+of+deliberate+linguistic+metaphor%2E+In+Proceedings+of+the+4th+Workshop+on+Figurative+La)
16. Lucía Pitarch, Jordi Bernad, Sergio-Luis Ojeda-Trueba, Alec Sánchez-Montero, Max Ionov, Emma Anglés-Herrero, Ángel Óscar Corona Beomont, and Gemma Bel-Enguix. 2026. Medical-flavors-aecc: Spanish oncological metaphors dataset. In Press. Accepted at CL4H@LREC 2026. [find](https://scholar.google.com/scholar?q=Luc%C3%ADa+Pitarch%2C+Jordi+Bernad%2C+Sergio%2DLuis+Ojeda%2DTrueba%2C+Alec+S%C3%A1nchez%2DMontero%2C+Max+Ionov%2C+Emma+Angl%C3%A9s%2DHerrero%2C+%C3%81ngel+%C3%93scar+Corona+Beomont%2C+and+Gemma+Bel%2DEnguix%2E+2026%2E+Medical%2Dflavors%2Daecc%3A+Spanish+oncol)
17. Mohamad Elzohbi and Richard Zhao. 2024. ContrastWSD: Enhancing metaphor detection with word sense disambiguation following the metaphor identification procedure. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 202… [find](https://scholar.google.com/scholar?q=Mohamad+Elzohbi+and+Richard+Zhao%2E+2024%2E+ContrastWSD%3A+Enhancing+metaphor+detection+with+word+sense+disambiguation+following+the+metaphor+identification+procedure%2E+In+Proceedings+of+the+2024+Joint+Inter)
18. Elisa Sanchez-Bayona and Rodrigo Agerri. 2022. Leveraging a new Spanish corpus for multilingual and cross-lingual metaphor detection. In Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL), pages 228–240, Abu Dhabi, United Arab Emirates (Hybrid). Association for Com… [find](https://scholar.google.com/scholar?q=Elisa+Sanchez%2DBayona+and+Rodrigo+Agerri%2E+2022%2E+Leveraging+a+new+Spanish+corpus+for+multilingual+and+cross%2Dlingual+metaphor+detection%2E+In+Proceedings+of+the+26th+Conference+on+Computational+Natural+Lan)
19. Alec Sánchez-Montero, Gemma Bel-Enguix, Sergio-Luis Ojeda-Trueba, and Gerardo Sierra. 2025. Disagreement in metaphor annotation of Mexican Spanish science tweets. In Proceedings of Context and Meaning: Navigating Disagreements in NLP Annotation, pages 155– 164, Abu Dhabi, UAE. International Committe… [find](https://scholar.google.com/scholar?q=Alec+S%C3%A1nchez%2DMontero%2C+Gemma+Bel%2DEnguix%2C+Sergio%2DLuis+Ojeda%2DTrueba%2C+and+Gerardo+Sierra%2E+2025%2E+Disagreement+in+metaphor+annotation+of+Mexican+Spanish+science+tweets%2E+In+Proceedings+of+Context+and+Meaning)
20. Elena Semino, Zsófia Demjén, Andrew Hardie, Sheila Payne, and Paul Rayson. 2017. Metaphor, cancer and the end of life: A corpus-based study. Routledge. [find](https://scholar.google.com/scholar?q=Elena+Semino%2C+Zs%C3%B3fia+Demj%C3%A9n%2C+Andrew+Hardie%2C+Sheila+Payne%2C+and+Paul+Rayson%2E+2017%2E+Metaphor%2C+cancer+and+the+end+of+life%3A+A+corpus%2Dbased+study%2E+Routledge%2E)
21. Wei Song, Shuhui Zhou, Ruiji Fu, Ting Liu, and Lizhen Liu. 2021. Verb metaphor detection via contextual relation learning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1:… [find](https://scholar.google.com/scholar?q=Wei+Song%2C+Shuhui+Zhou%2C+Ruiji+Fu%2C+Ting+Liu%2C+and+Lizhen+Liu%2E+2021%2E+Verb+metaphor+detection+via+contextual+relation+learning%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computationa)
22. Chang Su, Kechun Wu, and Yijiang Chen. 2021. Enhanced metaphor detection via incorporation of external knowledge based on linguistic theories. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1280–1287, Online. Association for Computational Linguistics. *Figure 5:… [find](https://scholar.google.com/scholar?q=Chang+Su%2C+Kechun+Wu%2C+and+Yijiang+Chen%2E+2021%2E+Enhanced+metaphor+detection+via+incorporation+of+external+knowledge+based+on+linguistic+theories%2E+In+Findings+of+the+Association+for+Computational+Linguist)

*Updated 2 November 2026*