BriefGPT.xyz
Apr, 2021
HLE-UPC在SemEval-2021任务5中的表现：用于检测有害语句的多层DistilBERT
HLE-UPC at SemEval-2021 Task 5: Multi-Depth DistilBERT for Toxic Spans Detection
HTML
PDF
Rafel Palliser, Albert Rial
TL;DR
研究使用多深度DistilBERT模型来检测文本中的有毒片段，定量结果表明使用多个深度的嵌入可提高模型性能，并定性分析了最佳模型。
Abstract
This paper presents our submission to
semeval-2021
Task 5:
toxic spans detection
. The purpose of this task is to detect the spans that make a text toxic, which is a complex labour for several reasons. Firstly, be
→