000131319 001__ 131319 000131319 005__ 20240207154753.0 000131319 0247_ $$2doi$$a10.18653/v1/2023.acl-long.308 000131319 0248_ $$2sideral$$a136802 000131319 037__ $$aART-2023-136802 000131319 041__ $$aeng 000131319 100__ $$0(orcid)0000-0002-6734-8808$$aPitarch, Lucia$$uUniversidad de Zaragoza 000131319 245__ $$aNo clues good clues: out of context Lexical Relation Classification 000131319 260__ $$c2023 000131319 5060_ $$aAccess copy available to the general public$$fUnrestricted 000131319 5203_ $$aThe accurate prediction of lexical relations between words is a challenging task in Natural Language Processing (NLP). The most recent advances in this direction come with the use of pre-trained language models (PTLMs). A PTLM typically needs “well-formed” verbalized text to interact with it, either to fine-tune it or to exploit it. However, there are indications that commonly used PTLMs already encode enough linguistic knowledge to allow the use of minimal (or none) textual context for some linguistically motivated tasks, thus notably reducing human effort, the need for data pre-processing, and favoring techniques that are language neutral since do not rely on syntactic structures. In this work, we explore this idea for the tasks of lexical relation classification (LRC) and graded Lexical Entailment (LE). After fine-tuning PTLMs for LRC with different verbalizations, our evaluation results show that very simple prompts are competitive for LRC and significantly outperform graded LE SoTA. In order to gain a better insight into this phenomenon, we perform a number of quantitative statistical analyses on the results, as well as a qualitative visual exploration based on embedding projections. 000131319 536__ $$9info:eu-repo/grantAgreement/ES/AEI/PID2020-113903RB-I00$$9info:eu-repo/grantAgreement/EC/HORIZON EUROPE/101057332/EU/Design-based Data-Driven Decision-support Tools: Producing Improved Cancer Outcomes Through User-Centred Research/4D PICTURE$$9info:eu-repo/grantAgreement/ES/MINECO/RYC2019-028112-I 000131319 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/ 000131319 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion 000131319 700__ $$0(orcid)0000-0001-8531-353X$$aBernad, Jordi$$uUniversidad de Zaragoza 000131319 700__ $$0(orcid)0000-0002-9169-5287$$aDranca, Lacramioara 000131319 700__ $$0(orcid)0000-0003-4239-8785$$aBobed Lisbona, Carlos$$uUniversidad de Zaragoza 000131319 700__ $$0(orcid)0000-0001-6452-7627$$aGracia, Jorge$$uUniversidad de Zaragoza 000131319 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf. 000131319 773__ $$g1 (2023), 5607--5625$$pProc. conf.- Assoc. Comput. Linguist., Meet.$$tProceedings of the conference - Association for Computational Linguistics. Meeting$$x0736-587X 000131319 8564_ $$s1692845$$uhttps://zaguan.unizar.es/record/131319/files/texto_completo.pdf$$yVersión publicada 000131319 8564_ $$s2856632$$uhttps://zaguan.unizar.es/record/131319/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada 000131319 909CO $$ooai:zaguan.unizar.es:131319$$particulos$$pdriver 000131319 951__ $$a2024-02-07-14:40:24 000131319 980__ $$aARTICLE