arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.14548cs.CL
收藏

ChatGPT问世后立场检测技术将如何演进?

How would Stance Detection Techniques Evolve after the Launch of ChatGPT?

College of Big Data and Internet, Shenzhen Technology University(深圳技术大学大数据与互联网学院);Faculty of Information and Intelligence, Shenzhen X-Institute(深圳X研究所信息与智能学院);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

Bowen Zhang, Daijun Ding, Liwen Jing, Genan Dai, Nan Yin

AI总结:

该研究探讨ChatGPT对立场检测领域的影响,实验证实其在常用数据集上性能达最优或相近水平,且具备预测解释能力,有望改变该领域研究范式,推动可解释AI构建。

摘要:

立场检测指从给定文本中提取针对某一目标的立场(支持、反对或中立)的任务。随着社交媒体内容的激增,该研究受到越来越多的关注。传统的立场检测处理框架是将其转化为文本分类任务。在解决这类问题时,深度学习模型已经取代了基于规则的模型和传统机器学习模型。当前的深度神经网络面临两大主要挑战:一是社交媒体帖子中的标注数据和信息不足,二是深度学习模型的不可解释性。2022年11月30日,新型预训练语言模型ChatGPT发布。针对立场检测任务,我们的实验表明,在SemEval-2016和P-Stance等常用数据集上,ChatGPT能够达到SOTA(当前最优)或相近的性能。同时,ChatGPT可以为自身的预测提供解释,这是现有任何模型都不具备的能力。对于其无法给出分类结果的案例,相关解释尤其有用。ChatGPT有望成为自然语言处理领域立场检测任务的最佳AI模型,或者至少会改变该领域的研究范式。此外,ChatGPT也为构建立场检测领域的可解释AI开辟了可能。

英文摘要:

Stance detection refers to the task of extracting the standpoint (Favor, Against or Neither) towards a target in given texts. Such research gains increasing attention with the proliferation of social media contents. The conventional framework of handling stance detection is converting it into text classification tasks. Deep learning models have already replaced rule-based models and traditional machine learning models in solving such problems. Current deep neural networks are facing two main challenges which are insufficient labeled data and information in social media posts and the unexplainable nature of deep learning models. A new pre-trained language model chatGPT was launched on Nov 30, 2022. For the stance detection tasks, our experiments show that ChatGPT can achieve SOTA or similar performance for commonly used datasets including SemEval-2016 and P-Stance. At the same time, ChatGPT can provide explanation for its own prediction, which is beyond the capability of any existing model. The explanations for the cases it cannot provide classification results are especially useful. ChatGPT has the potential to be the best AI model for stance detection tasks in NLP, or at least change the research paradigm of this field. ChatGPT also opens up the possibility of building explanatory AI for stance detection.

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。

↑