proceeding

A Parallel Cross-Lingual Benchmark for Multimodal Idiomaticity Understanding

Dilara Torunoğlu-SelametIstanbul Technical UniversityDoğukan ArslanIstanbul Technical UniversityRodrigo WilkensUniversity of ExeterWei HeUniversity of ExeterDoruk EryiğitAlisher Navoi' Tashkent State University of UzbekThomas PickardUniversity of SheffieldAdriana Silvina PaganoFederal University of Minas GeraisAline VillavicencioUniversity of ExeterGülşen EryiğitIstanbul Technical UniversityÁgnes AbuczkiAlisher Navoi' Tashkent State University of UzbekAida CardosoAlisher Navoi' Tashkent State University of UzbekAlesia LazarenkaAlisher Navoi' Tashkent State University of UzbekDina AlmassovaAlisher Navoi' Tashkent State University of UzbekAmália MendesAlisher Navoi' Tashkent State University of UzbekAnna KanellopoulouAlisher Navoi' Tashkent State University of UzbekAntoni Brosa RodríguezAlisher Navoi' Tashkent State University of UzbekBaiba ValkovskaAlisher Navoi' Tashkent State University of UzbekBeata WójtowiczAlisher Navoi' Tashkent State University of UzbekBolette PedersenAlisher Navoi' Tashkent State University of UzbekCarlos Manuel Hidalgo-TerneroAlisher Navoi' Tashkent State University of UzbekChaya LiebeskindAlisher Navoi' Tashkent State University of UzbekDanka JokićAlisher Navoi' Tashkent State University of UzbekDiego AlvesAlisher Navoi' Tashkent State University of UzbekELENI TRIANTAFYLLIDIAlisher Navoi' Tashkent State University of UzbekErik VelldalAlisher Navoi' Tashkent State University of UzbekFred PhilippyAlisher Navoi' Tashkent State University of UzbekGiedre Valunaite OleskevicieneIeva RizgelienėAlisher Navoi' Tashkent State University of UzbekInguna SkadiņaAlisher Navoi' Tashkent State University of UzbekIrina LobzhanidzeAlisher Navoi' Tashkent State University of UzbekIsabell Stinessen HaugenJauza Akbar KritoAlisher Navoi' Tashkent State University of UzbekJelena MarkovićAlisher Navoi' Tashkent State University of UzbekJohanna MontiAlisher Navoi' Tashkent State University of UzbekJosue Alejandro SaucaKaja DobrovoljcAlisher Navoi' Tashkent State University of UzbekKingsley Oluchi UgwuanyiLaura RitumaAlisher Navoi' Tashkent State University of UzbekLilja ØvrelidMaha Tufail AgroAlisher Navoi' Tashkent State University of UzbekManzura AbjalovaAlisher Navoi' Tashkent State University of UzbekMaria ChatzigrigoriouAlisher Navoi' Tashkent State University of UzbekMaría del Mar Sánchez RamosMarija PendevskaAlisher Navoi' Tashkent State University of UzbekMasoumeh SeyyedrezaeiAlisher Navoi' Tashkent State University of UzbekMehrnoush ShamsfardAlisher Navoi' Tashkent State University of UzbekMomina AhsanAlisher Navoi' Tashkent State University of UzbekMuhammad Ahsan Riaz KhanNathalie Carmen Hau NormanNilay Erdem AyyıldızAlisher Navoi' Tashkent State University of UzbekNina Hosseini-KivananiAlisher Navoi' Tashkent State University of UzbekNoémi Ligeti-NagyAlisher Navoi' Tashkent State University of UzbekNumaan NaeemOlha KanishchevaAlisher Navoi' Tashkent State University of UzbekOlha YatsyshynaDaniil OrelPetra GiommarelliAlisher Navoi' Tashkent State University of UzbekPetya OsenovaRadovan GarabíkAlisher Navoi' Tashkent State University of UzbekRegina E. SemouAlisher Navoi' Tashkent State University of UzbekRozane Rodrigues RebechiSalsabila Zahirah PranidaAlisher Navoi' Tashkent State University of UzbekSamia TouilebAlisher Navoi' Tashkent State University of UzbekSanni NimbAlisher Navoi' Tashkent State University of UzbekSarfraz AhmadAlisher Navoi' Tashkent State University of UzbekSarvinoz SharipovaAlisher Navoi' Tashkent State University of UzbekShahar GolanAlisher Navoi' Tashkent State University of UzbekShaoxiong JiSopuruchi Christian AbohAlisher Navoi' Tashkent State University of UzbekSrđan R. ŠućurAlisher Navoi' Tashkent State University of UzbekΣτέλλα ΜαρκαντωνάτουAlisher Navoi' Tashkent State University of UzbekSussi OlsenVahide TajalliAlisher Navoi' Tashkent State University of UzbekVeronika LippAlisher Navoi' Tashkent State University of UzbekVoula GiouliYelda Yeşildal EraydınZahra SaaberiAlisher Navoi' Tashkent State University of UzbekZhuohan Xie

2026en

Ochiq kirishBronza

ABI

Annotatsiya

Potentially idiomatic expressions (PIEs) carry meanings inherently tied to the everyday experience of a given language community.As such, they constitute an interesting challenge for assessing the linguistic (and to some extent cultural) capabilities of NLP systems.In this paper, we present XMPIE, a parallel multilingual and multimodal dataset of potentially idiomatic expressions.The dataset, containing 34 languages and over ten thousand items, allows comparative analyses of idiomatic patterns among language-specific realisations and preferences in order to gather insights about shared cultural aspects.This parallel dataset allows evaluation of language model performance for a given PIE in different languages and whether idiomatic understanding in one language can be transferred to another.Moreover, the dataset supports the study of PIEs across textual and visual modalities, to measure to what extent PIE understanding in one modality transfers or implies in understanding in another modality (text vs. image).The data was created by language experts, with both textual and visual components crafted under multilingual guidelines, and each PIE is accompanied by five images representing a spectrum from idiomatic to literal meanings, including semantically related and random distractors.The result is a high-quality benchmark for evaluating multilingual and multimodal idiomatic language understanding.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.63317/5cvnbcoktfo2

Iqtiboslar va manbalar

0 ta iqtibos0 ta foydalanilgan manba