arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.15420cs.CL
收藏

让预训练语言模型为短文本主题建模“想象”

Let the Pretrained Language Models "Imagine" for Short Texts Topic Modeling

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Pritom Saha Akash, Jie Huang, Kevin Chen-Chuan Chang

AI总结:

提出利用预训练语言模型将短文本扩展为长序列并结合神经主题模型减少噪声,有效解决短文本主题建模中的数据稀疏问题,生成高质量主题。

摘要:

主题模型是发现文档集合中潜在语义的引人注目的方法之一。然而,它假设文档具有足够的共现信息才能有效。但是在短文本中,共现信息极少,这导致文档表示中的特征稀疏。因此,现有的主题模型(概率或神经模型)大多无法从中挖掘模式以生成连贯的主题。在本文中,我们采用一种新的短文本主题建模方法来解决数据稀疏问题,通过使用现有的预训练语言模型(PLMs)将短文本扩展为更长的序列。此外,我们提供了一个简单的解决方案,扩展神经主题模型以减少来自PLMs的噪声非主题文本生成的影响。我们观察到我们的模型可以显著提升短文本主题建模的性能。在极端数据稀疏场景下对多个真实世界数据集的广泛实验表明,我们的模型能够生成高质量的主题,优于最先进的模型。

英文摘要:

Topic models are one of the compelling methods for discovering latent semantics in a document collection. However, it assumes that a document has sufficient co-occurrence information to be effective. However, in short texts, co-occurrence information is minimal, which results in feature sparsity in document representation. Therefore, existing topic models (probabilistic or neural) mostly fail to mine patterns from them to generate coherent topics. In this paper, we take a new approach to short-text topic modeling to address the data-sparsity issue by extending short text into longer sequences using existing pre-trained language models (PLMs). Besides, we provide a simple solution extending a neural topic model to reduce the effect of noisy out-of-topics text generation from PLMs. We observe that our model can substantially improve the performance of short-text topic modeling. Extensive experiments on multiple real-world datasets under extreme data sparsity scenarios show that our models can generate high-quality topics outperforming state-of-the-art models.

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。

↑