TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks

Viktor Moskvoretskii, Ekaterina Neminova, Alina Lobanova, Alexander Panchenko, Irina Nikishina


Abstract
In this paper, we explore the capabilities of LLMs in capturing lexical-semantic knowledge from WordNet on the example of the LLaMA-2-7b model and test it on multiple lexical semantic tasks. As the outcome of our experiments, we present TaxoLLaMA, the “all-in-one” model for taxonomy-related tasks, lightweight due to 4-bit quantization and LoRA. TaxoLLaMA achieves 11 SOTA results, and 4 top-2 results out of 16 tasks on the Taxonomy Enrichment, Hypernym Discovery, Taxonomy Construction, and Lexical Entailment tasks. Moreover, it demonstrates a very strong zero-shot performance on Lexical Entailment and Taxonomy Construction with no fine-tuning. We also explore its hidden multilingual and domain adaptation capabilities with a little tuning or few-shot learning. All datasets, code, and pre-trained models are available online (code: https://github.com/VityaVitalich/TaxoLLaMA)
Anthology ID:
2024.acl-long.127
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2331–2350
Language:
URL:
https://aclanthology.org/2024.acl-long.127
DOI:
Bibkey:
Cite (ACL):
Viktor Moskvoretskii, Ekaterina Neminova, Alina Lobanova, Alexander Panchenko, and Irina Nikishina. 2024. 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), pages 2331–2350, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks (Moskvoretskii et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.acl-long.127.pdf