Jan, 2021
基于语言封装和语义融合的在线内容广义索赔检测
LESA: Linguistic Encapsulation and Semantic Amalgamation Based
Generalised Claim Detection from Online Content
TL;DRLESA framework proposes a generalized model for argument mining using syntactic and contextual features to segregate claims, resolving the issue of unavailability of labeled unstructured text by annotating a Twitter dataset and improving state-of-the-art performances on benchmark claim datasets.