Tag
Introduces MIRA-Ev, a clinical argument mining benchmark built on Spanish MIR licensing-exam cases, annotated with span-level premises, claims, and support/attack relations, available in Spanish, English, and Basque. It provides a three-tier task hierarchy for evaluating evidence sentence retrieval, argumentative component extraction, and relation classification, addressing the limitations of multiple-choice QA benchmarks in clinical NLP.
This paper introduces BanglaMemeEvidence, a multimodal dataset of 2,917 Bengali memes annotated for explanatory evidence detection, and proposes BengaliMemeEvidenceNet, a hybrid framework achieving an F1 score of 0.74.