The paper discusses SemEval-2022 Task 7, a task about rating the plausibility of clarifications in English instructional texts. The dataset includes manually clarified how-to guides, and the task of the participating systems was to automatically determine the plausibility of a clarification in the respective context. The best system achieved an accuracy of 68.9%. The paper also shows that the top participating team could identify contexts with multiple plausible clarifications with an accuracy of 75.2%. The study contributes to the understanding of language ambiguity and the role of NLP systems in dealing with it.
Publication date: 21 Sep 2023
Project Page: https://github.com/acidAnn/claire
Paper: https://arxiv.org/pdf/2309.12102
