---
title: "Inferring Adjective Hypernyms with Language Models to Increase"
description: "To support the idea, they build an English gold standard of hyponym–hypernym adjective pairs with… 38 references, cited by 1 paper here."
authors: ["Lorenzo Augello", "John P. McCrae"]
year: 2025
venue: "Proceedings of the 5th Conference on Language, Data and Knowledge: The 5th OntoLex Workshop"
source: "https://aclanthology.org/2025.ontolex-1.1/"
arxiv: "2506.10715"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/augello-2025-inferring-adjective-hypernyms-language-models/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/augello-2025-inferring-adjective-hypernyms-language-models/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/17/) / Inferring Adjective Hypernyms with Language Models to Increase the Connectivity of Open English Wordnet

# Inferring Adjective Hypernyms with Language Models to Increase the Connectivity of Open English Wordnet

**Authors:** [Lorenzo Augello](https://md.research.elamur.ai/free/en/authors/lorenzo-augello/) and [John P. McCrae](https://md.research.elamur.ai/free/en/authors/john-p-mccrae/) · **Year:** 2025 · **Venue:** Proceedings of the 5th Conference on Language, Data and Knowledge: The 5th OntoLex Workshop · **Publisher:** [Unior Press](https://md.research.elamur.ai/free/en/publishers/unior-press/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.ontolex-1.1/) · [PDF](https://aclanthology.org/2025.ontolex-1.1.pdf) · [arXiv 2506.10715](https://arxiv.org/abs/2506.10715) · [OpenAlex](https://openalex.org/W4417355674)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/augello-2025-inferring-adjective-hypernyms-language-models/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Open English Wordnet (OEWN), published as OntoLex-lemon linked data, has no hypernym links between adjectives. Its hierarchy covers only nouns and verbs, so a large share of adjective synsets are isolated in the graph. Augello and McCrae argue that adjectives within one semantic field can still be ordered from narrower to broader meaning (for example, cognitive → mental → immaterial). They ground this in semantic inclusion and contrast it with the scalar, antonymy-based organisation of Princeton WordNet.

To support the idea, they build an English gold standard of hyponym–hypernym adjective pairs with definitions. The starting points are adjective hierarchies in Polish WordNet 3.0 and Open Dutch WordNet, followed by human annotation and validation against OEWN senses. The dataset is released in RDF using OntoLex.

They then test TaxoLLaMa and SmolLM-360M-Instruct in three settings: zero-shot, fine-tuned on single-answer data, and fine-tuned on multi-answer data, each with and without definitions. Fine-tuning on multiple valid hypernyms, with definitions in the prompt, works best. This shows the TaxoLLaMa recipe transfers to adjectives and offers a path towards a better-connected OEWN.

## Key points
- Princeton WordNet has 117,659 synsets and 84,428 hypernym–hyponym relations, all for nouns and verbs. Adjectives are linked only by antonymy, similarity and pertainymy.
- The gold standard comes in two versions:
  - a "single" set with one correct hypernym per item;
  - a "multiple" set that also accepts OEWN synonyms of the hypernym (e.g. "real" and "existent").
  - Data are on GitHub (lorenzoaugello/adjective-hypernymy) and models on Hugging Face.
- On the multiple set with definitions, TaxoLLaMa-ft-multi scores best: P 0.28, R 0.25, F 0.26. SmolLM-ft-multi reaches P 0.20, R 0.14, F 0.16. Zero-shot TaxoLLaMa gets only F 0.11.
- On the single set, base TaxoLLaMa beats the single-answer fine-tuned model on F1 (0.39 vs 0.31) because it returns a list of candidates. Counting only its top-ranked answer, just 7 of 14 correct hypernyms are in first place.
- The authors list four limitations: a small dataset, only two models tested, subjective annotation, and coverage of English only.

## Interesting ideas
- Bootstrapping an English gold standard from hierarchies that other-language wordnets already encode, then having humans check the senses, avoids annotating from scratch.
- Including the gloss in the prompt consistently improved the models, because it disambiguates which sense of a polysemous adjective is meant.
- Training and scoring against a set of acceptable answers (the gold hypernym plus its synonyms) rewards predictions that are correct but phrased differently, and it trained better models.
- Separating "any correct candidate in the list" from "correct candidate ranked first" showed that a list-producing model's F1 can overstate its precision.
- Treating adjective hypernymy as inclusion within a single semantic field, rather than as a global taxonomy, keeps the relation narrow and easier to defend.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (world): Polish or Dutch adjective hierarchies, mapped through interlingual links, could seed a "broader property" layer in our WordNet-based ontology, with each edge traceable to its source wordnet.
- **I2** (learn): when an LLM teacher tier proposes lexical relations, it should receive the synset definition rather than the bare lemma, so the silver labels are tied to a specific sense.
- **I3** (learn): evaluating our ontology-induction or teacher outputs against synset-level answer sets would stop near-synonym predictions from being counted as errors.
- **I4** (answer): QA and test scoring should report top-1 accuracy alongside list-based recall, so a reader that hedges with many candidates does not look stronger than it is.
- **I5** (frames): a property entailment such as "unpleasant ⇒ negative" could license explainable implicature or irony checks, without forcing adjectives into a noun-style tree.

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

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,959 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,789 works

🧭 Topics (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 4,145 works · [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,381 works · [📖 Lexical semantics & word embeddings](https://md.research.elamur.ai/free/en/topics/lexical-semantics/) · 69 works

## Cite

Cite as: Lorenzo Augello and John P. McCrae. 2025. Inferring Adjective Hypernyms with Language Models to Increase the Connectivity of Open English Wordnet. Proceedings of the 5th Conference on Language, Data and Knowledge: The 5th OntoLex Workshop.

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

```bibtex
@inproceedings{augello2025inferring,
  title = {{Inferring Adjective Hypernyms with Language Models to Increase the Connectivity of Open English Wordnet}},
  author = {Lorenzo Augello and John P. McCrae},
  booktitle = {Proceedings of the 5th Conference on Language, Data and Knowledge: The 5th OntoLex Workshop},
  year = {2025},
  eprint = {2506.10715},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.10715}
}
```

- [← previous HTU at MAHED Shared Task: Ensemble-Based Classification of Arabic Hate and Hope Speech Using Pre-trained Dialectal Arabic Models](https://md.research.elamur.ai/free/en/papers/saleh-2025-htu-mahed-shared-task-ensemble/)
- [next → Integrating Argumentation Features for Enhanced Propaganda Detection in Arabic Narratives on the Israeli War on Gaza](https://md.research.elamur.ai/free/en/papers/nabhani-2025-integrating-argumentation-features-enhanced-propaganda/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/17/)

## References

38 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Marco Baroni and Alessandro Lenci. 2011. [How we BLESSed distributional semantic evaluation](https://md.research.elamur.ai/free/en/papers/baroni-2011-how-we-blessed-distributional-semantic/). In Proceedings of the GEMS 2011 Workshop on GEometrical Models of Natural Language Semantics, pages 1–10, Edinburgh, UK. Association for Computational Linguistics.
2. Marti A. Hearst. 1992. [Automatic acquisition of hyponyms from large text corpora](https://md.research.elamur.ai/free/en/papers/hearst-1992-automatic-acquisition-hyponyms-large-text/). In Proceedings of the 14th Conference on Computational Linguistics -Volume 2, COLING ’92, page 539–545, USA. Association for Computational Linguistics.
3. Georgeta Bordea, Els Lefever, and Paul Buitelaar. 2016. SemEval-2016 task 13: Taxonomy extraction evaluation (TExEval-2). In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 1081–1091, San Diego, California. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Georgeta+Bordea%2C+Els+Lefever%2C+and+Paul+Buitelaar%2E+2016%2E+SemEval%2D2016+task+13%3A+Taxonomy+extraction+evaluation+%28TExEval%2D2%29%2E+In+Proceedings+of+the+10th+International+Workshop+on+Semantic+Evaluation+%28SemE)
4. Frans Heyvaert. 2010. An outline for a semantic categorization of adjectives. In Proceedings of the 14th EURALEX International Congress, pages 1309–1318, Leeuwarden/Ljouwert, The Netherlands. Fryske Akademy. [find](https://scholar.google.com/scholar?q=Frans+Heyvaert%2E+2010%2E+An+outline+for+a+semantic+categorization+of+adjectives%2E+In+Proceedings+of+the+14th+EURALEX+International+Congress%2C+pages+1309%E2%80%931318%2C+Leeuwarden%2FLjouwert%2C+The+Netherlands%2E+Fryske+A)
5. Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. [LoRA: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In International Conference on Learning Representations.
6. John P. McCrae, Christian Chiarcos, Francis Bond, Philipp Cimiano, Thierry Declerck, Gerard de Melo, Jorge Gracia, Sebastian Hellmann, Bettina Klimek, Steven Moran, Petya Osenova, Antonio Pareja-Lora, and Jonathan Pool. 2016. The open linguistics working group: Developing the linguistic linked open data cloud. In 10th Language Resource and Evaluation Conference (LREC), pages 2435–2441. [find](https://scholar.google.com/scholar?q=John+P%2E+McCrae%2C+Christian+Chiarcos%2C+Francis+Bond%2C+Philipp+Cimiano%2C+Thierry+Declerck%2C+Gerard+de+Melo%2C+Jorge+Gracia%2C+Sebastian+Hellmann%2C+Bettina+Klimek%2C+Steven+Moran%2C+Petya+Osenova%2C+Antonio+Pareja%2DLora%2C)
7. Franz Hundsnurscher and Jochen Splett. 1982. Grundle-gung Einer Semantischen Beschreibung der Adjektive des Deutschen, pages 16–47. VS Verlag für Sozial-wissenschaften, Wiesbaden. [find](https://scholar.google.com/scholar?q=Franz+Hundsnurscher+and+Jochen+Splett%2E+1982%2E+Grundle%2Dgung+Einer+Semantischen+Beschreibung+der+Adjektive+des+Deutschen%2C+pages+16%E2%80%9347%2E+VS+Verlag+f%C3%BCr+Sozial%2Dwissenschaften%2C+Wiesbaden%2E)
8. John P. McCrae, Michael Wayne Goodman, Francis Bond, Alexandre Rademaker, Ewa Rudnicka, and Luis Morgado Da Costa. 2021. The globalwordnet formats: Updates for 2020. In Proceedings of the 11th Global Wordnet Conference, pages 91–99. [↗](https://doi.org/10.18653/v1/2021.gwc-1.11)
9. Cristopher Kennedy. 2007. Vagueness and grammar: the semantics of relative and absolute gradable adjectives. Linguistics & Philosophy, 30:1–45. [find](https://scholar.google.com/scholar?q=Cristopher+Kennedy%2E+2007%2E+Vagueness+and+grammar%3A+the+semantics+of+relative+and+absolute+gradable+adjectives%2E+Linguistics+%26+Philosophy%2C+30%3A1%E2%80%9345%2E)
10. Thomas Kober, Julie Weeds, Lorenzo Bertolini, and David Weir. 2021. Data augmentation for hypernymy detection. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1034–1048, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Thomas+Kober%2C+Julie+Weeds%2C+Lorenzo+Bertolini%2C+and+David+Weir%2E+2021%2E+Data+augmentation+for+hypernymy+detection%2E+In+Proceedings+of+the+16th+Conference+of+the+European+Chapter+of+the+Association+for+Comp)
11. John P. McCrae, Francesca Quattri, Christina Unger, and Philipp Cimiano. 2014. Modelling the semantics of adjectives in the ontology-lexicon interface. In Proceedings of the 4th Workshop on Cognitive Aspects of the Lexicon (CogALex), pages 198–209, Dublin, Ireland. Association for Computational Linguistics and Dublin City University. [find](https://scholar.google.com/scholar?q=John+P%2E+McCrae%2C+Francesca+Quattri%2C+Christina+Unger%2C+and+Philipp+Cimiano%2E+2014%2E+Modelling+the+semantics+of+adjectives+in+the+ontology%2Dlexicon+interface%2E+In+Proceedings+of+the+4th+Workshop+on+Cognitive+)
12. Wei Liu, Ming Xiang, and Nai Ding. 2023. Adjective scale probe: Can language models encode formal semantics information? Proceedings of the AAAI Conference on Artificial Intelligence, 37(11):13282– 13290. [find](https://scholar.google.com/scholar?q=Wei+Liu%2C+Ming+Xiang%2C+and+Nai+Ding%2E+2023%2E+Adjective+scale+probe%3A+Can+language+models+encode+formal+semantics+information%3F+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+37%2811%29%3A13282%E2%80%93+13)
13. John P. McCrae, Alexandre Rademaker, Francis Bond, Ewa Rudnicka, and Christiane Fellbaum. 2019a. [find](https://scholar.google.com/scholar?q=John+P%2E+McCrae%2C+Alexandre+Rademaker%2C+Francis+Bond%2C+Ewa+Rudnicka%2C+and+Christiane+Fellbaum%2E+2019a%2E)
14. [English WordNet 2019 – an open-source WordNet for English](https://md.research.elamur.ai/free/en/papers/mccrae-2019-english-wordnet/). In Proceedings of the 10th Global Wordnet Conference, pages 245–252, Wroclaw, Poland. Global Wordnet Association.
15. John Lyons. 1977. Semantics. Cambridge University Press. [find](https://scholar.google.com/scholar?q=John+Lyons%2E+1977%2E+Semantics%2E+Cambridge+University+Press%2E)
16. Lovish Madaan, David Esiobu, Pontus Stenetorp, Barbara Plank, and Dieuwke Hupkes. 2024. Lost in inference: Rediscovering the role of natural language inference for large language models. [find](https://scholar.google.com/scholar?q=Lovish+Madaan%2C+David+Esiobu%2C+Pontus+Stenetorp%2C+Barbara+Plank%2C+and+Dieuwke+Hupkes%2E+2024%2E+Lost+in+inference%3A+Rediscovering+the+role+of+natural+language+inference+for+large+language+models%2E)
17. John P. McCrae, Alexandre Rademaker, Francis Bond, Ewa Rudnicka, and Christiane Fellbaum. 2019b. [English wordnet 2019 – an open-source wordnet for english](https://md.research.elamur.ai/free/en/papers/mccrae-2019-english-wordnet/). In Proceedings of the 10th Global WordNet Conference – GWC 2019.
18. Isa Maks, Piek Vossen, Roxane Segers, and Hennie van der Vliet. 2008. Adjectives in the Dutch semantic lexical database CORNETTO. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08), Marrakech, Morocco. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Isa+Maks%2C+Piek+Vossen%2C+Roxane+Segers%2C+and+Hennie+van+der+Vliet%2E+2008%2E+Adjectives+in+the+Dutch+semantic+lexical+database+CORNETTO%2E+In+Proceedings+of+the+Sixth+International+Conference+on+Language+Resou)
19. George A. Miller. 1995. [WordNet: a lexical database for English](https://md.research.elamur.ai/free/en/papers/miller-1994-wordnet/). Commun. ACM, 38(11):39–41. [↗](https://doi.org/10.1145/219717.219748)
20. Viktor Moskvoretskii, Ekaterina Neminova, Alina Lobanova, Alexander Panchenko, and Irina Nikishina. 2024a. TaxoLLaMA: WordNet-based model for solving multiple lexical semantic tasks. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), page 2331–2350. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Viktor+Moskvoretskii%2C+Ekaterina+Neminova%2C+Alina+Lobanova%2C+Alexander+Panchenko%2C+and+Irina+Nikishina%2E+2024a%2E+TaxoLLaMA%3A+WordNet%2Dbased+model+for+solving+multiple+lexical+semantic+tasks%2E+In+Proceedings+of)
21. Marek Maziarz, Maciej Piasecki, Ewa Rudnicka, Stan Szpakowicz, and Paweł K˛edzia. 2016. plWordNet 3.0 – a comprehensive lexical-semantic resource. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2259–2268, Osaka, Japan. [find](https://scholar.google.com/scholar?q=Marek+Maziarz%2C+Maciej+Piasecki%2C+Ewa+Rudnicka%2C+Stan+Szpakowicz%2C+and+Pawe%C5%82+K%CB%9Bedzia%2E+2016%2E+plWordNet+3%2E0+%E2%80%93+a+comprehensive+lexical%2Dsemantic+resource%2E+In+Proceedings+of+COLING+2016%2C+the+26th+International)
22. The COL-ING 2016 Organizing Committee. [find](https://scholar.google.com/scholar?q=The+COL%2DING+2016+Organizing+Committee%2E)
23. Viktor Moskvoretskii, Alexander Panchenko, and Irina Nikishina. 2024b. [Are large language models good at lexical semantics? a case of taxonomy learning](https://md.research.elamur.ai/free/en/papers/moskvoretskii-2024-are-large-language-models-good/). In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1498–1510, Torino, Italia. ELRA and ICCL.
24. Diana McCarthy and Roberto Navigli. 2007. [SemEval-2007 task 10: English lexical substitution task](https://md.research.elamur.ai/free/en/papers/mccarthy-2007-semeval-2007-task-10-english/). In Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007), pages 48–53, Prague, Czech Republic. Association for Computational Linguistics.
25. M. Lynne Murphy. 2003. Semantic relations and the lexicon: antonymy, synonymy, and other paradigms. Acta Linguistica Hafniensia, 36(1):185–189. [find](https://scholar.google.com/scholar?q=M%2E+Lynne+Murphy%2E+2003%2E+Semantic+relations+and+the+lexicon%3A+antonymy%2C+synonymy%2C+and+other+paradigms%2E+Acta+Linguistica+Hafniensia%2C+36%281%29%3A185%E2%80%93189%2E)
26. John P. McCrae. 2025. Renovating the verb hierarchy of english wordnet. In Global WordNet Conference 2025. [find](https://scholar.google.com/scholar?q=John+P%2E+McCrae%2E+2025%2E+Renovating+the+verb+hierarchy+of+english+wordnet%2E+In+Global+WordNet+Conference+2025%2E)
27. Marten Postma, Emiel van Miltenburg, Roxane Segers, Anneleen Schoen, and Piek Vossen. 2016. Open Dutch WordNet. In Proceedings of the 8th Global WordNet Conference (GWC), pages 302–310, Bucharest, Romania. Global Wordnet Association. [find](https://scholar.google.com/scholar?q=Marten+Postma%2C+Emiel+van+Miltenburg%2C+Roxane+Segers%2C+Anneleen+Schoen%2C+and+Piek+Vossen%2E+2016%2E+Open+Dutch+WordNet%2E+In+Proceedings+of+the+8th+Global+WordNet+Conference+%28GWC%29%2C+pages+302%E2%80%93310%2C+Bucharest%2C+Rom)
28. John P. McCrae, Julia Bosque-Gil, Jorge Gracia, Paul Buitelaar, and Philipp Cimiano. 2017. The ontolex-lemon model: development and applications. In Proceedings of eLex 2017, pages 587–597. [find](https://scholar.google.com/scholar?q=John+P%2E+McCrae%2C+Julia+Bosque%2DGil%2C+Jorge+Gracia%2C+Paul+Buitelaar%2C+and+Philipp+Cimiano%2E+2017%2E+The+ontolex%2Dlemon+model%3A+development+and+applications%2E+In+Proceedings+of+eLex+2017%2C+pages+587%E2%80%93597%2E)
29. I. Made Suwija Putra, Daniel Siahaan, and Ahmad Saikhu. 2024. Recognizing textual entailment: A review of resources, approaches, applications, and challenges. ICT Express, 10(1):132–155. Publisher Copyright: © 2023 The Author(s). [find](https://scholar.google.com/scholar?q=I%2E+Made+Suwija+Putra%2C+Daniel+Siahaan%2C+and+Ahmad+Saikhu%2E+2024%2E+Recognizing+textual+entailment%3A+A+review+of+resources%2C+approaches%2C+applications%2C+and+challenges%2E+ICT+Express%2C+10%281%29%3A132%E2%80%93155%2E+Publisher+Cop)
30. Asahi Ushio, Jose Camacho-Collados, and Steven Schockaert. 2021. Distilling relation embeddings from pretrained language models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9044–9062, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Asahi+Ushio%2C+Jose+Camacho%2DCollados%2C+and+Steven+Schockaert%2E+2021%2E+Distilling+relation+embeddings+from+pretrained+language+models%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+in+Natural+L)
31. Victor Raskin and Sergei Nirenburg. 1995. Lexical semantics of adjectives a microtheory of adjectival meaning. [find](https://scholar.google.com/scholar?q=Victor+Raskin+and+Sergei+Nirenburg%2E+1995%2E+Lexical+semantics+of+adjectives+a+microtheory+of+adjectival+meaning%2E)
32. Ivan Vulić, Daniela Gerz, Douwe Kiela, Felix Hill, and Anna Korhonen. 2017. [HyperLex: A large-scale evaluation of graded lexical entailment](https://md.research.elamur.ai/free/en/papers/vulic-2017-hyperlex-large-scale-evaluation-graded/). Computational Linguistics, 43(4):781–835.
33. Ewa Rudnicka, Wojciech Witkowski, and Katarzyna Podlaska. 2016. Challenges of adjective mapping between plWordNet and Princeton WordNet. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 2413–2418, Portorož, Slovenia. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Ewa+Rudnicka%2C+Wojciech+Witkowski%2C+and+Katarzyna+Podlaska%2E+2016%2E+Challenges+of+adjective+mapping+between+plWordNet+and+Princeton+WordNet%2E+In+Proceedings+of+the+Tenth+International+Conference+on+Languag)
34. Chengyu Wang, Minghui Qiu, Jun Huang, and Xiaofeng He. 2021. KEML: A knowledge-enriched meta-learning framework for lexical relation classification. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15):13924–13932. [find](https://scholar.google.com/scholar?q=Chengyu+Wang%2C+Minghui+Qiu%2C+Jun+Huang%2C+and+Xiaofeng+He%2E+2021%2E+KEML%3A+A+knowledge%2Denriched+meta%2Dlearning+framework+for+lexical+relation+classification%2E+Proceedings+of+the+AAAI+Conference+on+Artificial+In)
35. Enrico Santus, Frances Yung, Alessandro Lenci, and Chu-Ren Huang. 2015. EVALution 1.0: an evolving semantic dataset for training and evaluation of distributional semantic models. In Proceedings of the 4th Workshop on Linked Data in Linguistics: Resources and Applications, pages 64–69, Beijing, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Enrico+Santus%2C+Frances+Yung%2C+Alessandro+Lenci%2C+and+Chu%2DRen+Huang%2E+2015%2E+EVALution+1%2E0%3A+an+evolving+semantic+dataset+for+training+and+evaluation+of+distributional+semantic+models%2E+In+Proceedings+of+the)
36. Silke Scheible and Sabine Schulte im Walde. 2014. A database of paradigmatic semantic relation pairs for German nouns, verbs, and adjectives. In Proceedings of Workshop on Lexical and Grammatical Resources for Language Processing, pages 111–119, Dublin, Ireland. Association for Computational Linguistics and Dublin City University. [find](https://scholar.google.com/scholar?q=Silke+Scheible+and+Sabine+Schulte+im+Walde%2E+2014%2E+A+database+of+paradigmatic+semantic+relation+pairs+for+German+nouns%2C+verbs%2C+and+adjectives%2E+In+Proceedings+of+Workshop+on+Lexical+and+Grammatical+Reso)
37. Erik Tjong Kim Sang. 2007. Extracting hypernym pairs from the web. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions, pages 165–168, Prague, Czech Republic. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Erik+Tjong+Kim+Sang%2E+2007%2E+Extracting+hypernym+pairs+from+the+web%2E+In+Proceedings+of+the+45th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+Companion+Volume+Proceedings+of+the+Demo+a)
38. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller, Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez, Madian Khabsa, Isabel Kloumann, Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov, Pushkar Mishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith, Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu, Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan, Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, and Thomas Scialom. 2023. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/).

*Updated 4 November 2026*