arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.18239cs.CLcs.AI
收藏

基于零样本提示的分类:基础模型时代下德语推文的主题标注

Zero-shot prompt-based classification: topic labeling in times of foundation models in German Tweets

University Trier(特里尔大学);krAil

Simon Münker, Kai Kugler, Achim Rettinger

AI总结:

本研究在德语推文主题标注任务中实证评估零样本提示分类,证明其效果与微调BERT相当,且无需标注训练数据,凸显NLP领域范式转变。

摘要:

过滤和标注文本数据是许多领域(如社交媒体或新闻分析)中的常规任务。自动化这些任务可以在分析速度和内容覆盖广度上实现扩展,并减少所需的人工工作量。由于自然语言处理技术的进步,特别是大型基础模型的成功,一种新的自动化标注流程工具已经问世,该工具通过文本到文本的接口,在提供书面指南的情况下,无需提供训练样本即可进行标注。在本研究中,我们在实际环境中评估了这些进展,通过对关于欧洲社会和政治危机的德语Twitter数据进行标注任务的实证测试。我们将基于提示的结果与我们的人工标注以及先前的分类方法(包括朴素贝叶斯和基于BERT的微调/领域适应流程)进行了比较。我们的结果表明,尽管在模型选择过程中受到本地计算资源的限制,基于提示的方法与微调的BERT相当,但无需任何标注的训练数据。我们的发现强调了自然语言处理领域正在进行的范式转变,即下游任务的统一以及对预标注训练数据需求的消除。

英文摘要:

Filtering and annotating textual data are routine tasks in many areas, like social media or news analytics. Automating these tasks allows to scale the analyses wrt. speed and breadth of content covered and decreases the manual effort required. Due to technical advancements in Natural Language Processing, specifically the success of large foundation models, a new tool for automating such annotation processes by using a text-to-text interface given written guidelines without providing training samples has become available. In this work, we assess these advancements in-the-wild by empirically testing them in an annotation task on German Twitter data about social and political European crises. We compare the prompt-based results with our human annotation and preceding classification approaches, including Naive Bayes and a BERT-based fine-tuning/domain adaptation pipeline. Our results show that the prompt-based approach - despite being limited by local computation resources during the model selection - is comparable with the fine-tuned BERT but without any annotated training data. Our findings emphasize the ongoing paradigm shift in the NLP landscape, i.e., the unification of downstream tasks and elimination of the need for pre-labeled training data.

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。

↑