arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.02709cs.CLcs.AI
收藏

德语文本嵌入聚类基准

German Text Embedding Clustering Benchmark

Hasso Plattner Institute, University of Potsdam(哈索·普拉特纳研究所,波茨坦大学)

Silvan Wehrli, Bert Arnrich, Christopher Irrgang

AI总结:

本文提出了一个德语文本嵌入聚类基准,评估了多种单语和多语言模型在不同聚类算法下的表现,发现降低嵌入维度可改善聚类,且对短文本进行持续预训练能显著提升性能。

摘要:

本工作引入了一个基准,用于评估在不同领域中对德语文本嵌入进行聚类的性能。该基准的提出是由于在需要对文本进行分组的任务(如主题建模)中,聚类神经文本嵌入的使用日益增加,且现有基准缺乏德语资源。我们提供了一项初步分析,针对一系列预训练的单语和双语模型,评估其在不同聚类算法结果上的表现。结果包括表现优异的单语和双语模型。降低嵌入的维度可以进一步改善聚类效果。此外,我们使用 German BERT 模型进行了持续预训练实验,以评估这一额外训练的益处。实验表明,对于短文本,可以实现显著的性能提升。所有代码和数据集均已公开。

英文摘要:

This work introduces a benchmark assessing the performance of clustering German text embeddings in different domains. This benchmark is driven by the increasing use of clustering neural text embeddings in tasks that require the grouping of texts (such as topic modeling) and the need for German resources in existing benchmarks. We provide an initial analysis for a range of pre-trained mono- and multilingual models evaluated on the outcome of different clustering algorithms. Results include strong performing mono- and multilingual models. Reducing the dimensions of embeddings can further improve clustering. Additionally, we conduct experiments with continued pre-training for German BERT models to estimate the benefits of this additional training. Our experiments suggest that significant performance improvements are possible for short text. All code and datasets are publicly available.

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。

↑