arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2111.04052cs.CL
收藏

预训练的Transformer如何集成上下文关键字?应用于人道主义计算

How does a Pre-Trained Transformer Integrate Contextual Keywords? Application to Humanitarian Computing

European Commission Joint Research Centre(欧洲委员会联合研究中心)

Barriere Valentin, Jacquet Guillaume

摘要:

在分类任务中,处理文本片段和元数据通常需要处理多模态方法。当这些元数据是文本的时候,为了利用模型内部编码的语义信息,很容易将它们与预先训练的Transformer一起使用。本文描述了如何通过将危机事件类型添加到要分类的每个推文来改进人道主义分类任务。基于模型权重和行为的附加实验,它识别了所提出的神经网络方法如何部分地过度拟合危机基准的特殊性,以更好地突出模型如何毫无疑问地学习使用和利用元数据的文本语义。

英文摘要:

In a classification task, dealing with text snippets and metadata usually requires dealing with multimodal approaches. When those metadata are textual, it is tempting to use them intrinsically with a pre-trained transformer, in order to leverage the semantic information encoded inside the model. This paper describes how to improve a humanitarian classification task by adding the crisis event type to each tweet to be classified. Based on additional experiments of the model weights and behavior, it identifies how the proposed neural network approach is partially over-fitting the particularities of the Crisis Benchmark, to better highlight how the model is still undoubtedly learning to use and take advantage of the metadata's textual semantics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑