cs.CL · 2608.23037 Copy arXiv ID · Aug 24, 2026 Save The Multilingual FrameNet Corpus Authors: Beatrice Fiumanò , Nicolas Lazzari , Simone Paolo Ponzetto , Valentina Presutti
Organizations: University of Bologna, Italy · University of Pisa, Italy · University of Mannheim, Germany
Abstract This paper introduces the Multilingual FrameNet Corpus (mFNC), a novel resource that extends the English Berkeley FrameNet corpus by collecting and harmonizing existing language-specific corpora across nine additional languages: Brazilian Portuguese, Chinese, Dutch, French, German, Italian, Korean, Latvian and Swedish. By training models that rely on different architectures on the mFNC, we consistently outperform existing state-of-the-art Frame Semantic Parsers in both multilingual and cross-lingual settings, underscoring the importance of multilingual training data. The mFNC and our trained FSP models are openly available at https://github.com/beatrice-f/mFNC .
Explore similar work Sep 3, 2026 · Chihiro Yano, Ryohei Sasano Multilingual Language Model Evaluation LLM Evaluation
Graduate School of Informatics, Nagoya University
Feb 25, 2026 · Barah Fazili, Koustava Goswami Cross-Lingual Representation Alignment Multilingual Language Models
IIT Bombay, Mumbai, India · Adobe Research, Bangalore, India
Jul 1, 2026 · Maximilian Idahl, Jörg Tiedemann, Sampo Pyysalo +19 Language Model Pretraining Synthetic Data Pretraining
ellamind · Leibniz University Hannover · University of Helsinki +14
Sep 3, 2026 J/K move · Enter open · S save
Chihiro Yano, Ryohei Sasano
Graduate School of Informatics, Nagoya University
In frame semantics, sentence comprehension is assumed to proceed by relating lexical meaning to background knowledge called semantic frames, thereby enabling readers to implicitly enrich the text with unstated information. Recent large language models (LLMs) have achieved strong performance across a wide range of downstream tasks. However, it remains unclear whether they can reproduce the kinds of implicit enrichment that humans naturally make during comprehension. To address this question, we introduce FrameBench, a benchmark grounded in frame semantics. FrameBench consists of multiple-choice questions that test whether models distinguish the frames evoked by the same verb across contexts. We construct the benchmark for English and Japanese using FrameNet-style resources and a generation-and-verification pipeline with native-speaker judgments. Our experiments on a diverse set of models reveal challenges for small models, while several large models surpass the human reference scores. We release the constructed FrameBench dataset and the code for dataset construction and evaluation at https://github.com/SasanoLab/FrameBench.