arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.09894cs.CL
收藏

短文本聚类的表示学习

Representation Learning for Short Text Clustering

Deakin University(迪肯大学);University of Technology Sydney(悉尼科技大学)

Hui Yin, Xiangyu Song, Shuiqiao Yang, Guangyan Huang, Jianxin Li

摘要:

由于短文本语料的稀疏性、高维性和噪声性,有效的表示学习是短文本聚类的关键。现有的预训练模型(例如,Word 2 vec和BERT)与传统的词袋(Bag-of-Words,BoW)模型相比,大大提高了短文本表示的表达能力,具有更精简、低维和连续的特征。然而,这些模型是为了通用目的而训练的,因此对于短文本聚类任务来说是次优的。在本文中,我们提出了两种方法来利用无监督自动编码器(AE)框架,根据这些预训练的文本模型进一步调整短文本表示,以获得最佳聚类性能。第一种方法STN-GAE(Structural Text Network Graph Autoencoder)通过构建文本网络,充分利用语料库中的结构化文本信息,然后采用图卷积网络作为编码器,将结构化特征与预先训练好的文本特征融合,进行文本表示学习。在我们的第二种方法软聚类分配自动编码器(SCA-AE)中,我们对自动编码器的潜在空间采用了额外的软聚类分配约束,以鼓励学习的文本表示更加聚类友好。我们在7个流行的短文本数据集上对两种方法进行了测试,实验结果表明,当只使用预训练好的模型进行短文本聚类时,BERT的性能优于BoW和Word 2 vec。然而,只要我们进一步调整预训练的表示,所提出的方法,如SCA-AE可以大大提高聚类性能,与单独使用BERT相比,准确率提高可以达到14%。

英文摘要:

Effective representation learning is critical for short text clustering due to the sparse, high-dimensional and noise attributes of short text corpus. Existing pre-trained models (e.g., Word2vec and BERT) have greatly improved the expressiveness for short text representations with more condensed, low-dimensional and continuous features compared to the traditional Bag-of-Words (BoW) model. However, these models are trained for general purposes and thus are suboptimal for the short text clustering task. In this paper, we propose two methods to exploit the unsupervised autoencoder (AE) framework to further tune the short text representations based on these pre-trained text models for optimal clustering performance. In our first method Structural Text Network Graph Autoencoder (STN-GAE), we exploit the structural text information among the corpus by constructing a text network, and then adopt graph convolutional network as encoder to fuse the structural features with the pre-trained text features for text representation learning. In our second method Soft Cluster Assignment Autoencoder (SCA-AE), we adopt an extra soft cluster assignment constraint on the latent space of autoencoder to encourage the learned text representations to be more clustering-friendly. We tested two methods on seven popular short text datasets, and the experimental results show that when only using the pre-trained model for short text clustering, BERT performs better than BoW and Word2vec. However, as long as we further tune the pre-trained representations, the proposed method like SCA-AE can greatly increase the clustering performance, and the accuracy improvement compared to use BERT alone could reach as much as 14\%.

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。

↑