arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.05119cs.CL
收藏

微调之外:少样本句子嵌入迁移

Beyond Fine-tuning: Few-Sample Sentence Embedding Transfer

Amazon Alexa AI Search(亚马逊Alexa人工智能搜索);Microsoft(微软);University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Siddhant Garg, Rohit Kumar Sharma, Yingyu Liang

摘要:

在小数据集上微调(FT)预训练的句子嵌入模型已被证明具有局限性。在本文中,我们表明,将来自预训练模型的嵌入与来自仅在目标数据上训练的简单句子嵌入模型的嵌入相连接,可以提高FT在少样本任务中的性能。为此,通过冻结嵌入模型权重或端到端地训练分类器和嵌入模型,在组合的嵌入上训练线性分类器。我们对来自NLP任务的七个小数据集进行了评估,并表明我们的端到端训练方法在计算开销可以忽略不计的情况下优于FT。此外,我们还表明,复杂的组合技术,如CCA和KCCA不工作,以及在实践中串联。我们提供理论分析来解释这一经验观察结果。

英文摘要:

Fine-tuning (FT) pre-trained sentence embedding models on small datasets has been shown to have limitations. In this paper we show that concatenating the embeddings from the pre-trained model with those from a simple sentence embedding model trained only on the target data, can improve over the performance of FT for few-sample tasks. To this end, a linear classifier is trained on the combined embeddings, either by freezing the embedding model weights or training the classifier and embedding models end-to-end. We perform evaluation on seven small datasets from NLP tasks and show that our approach with end-to-end training outperforms FT with negligible computational overhead. Further, we also show that sophisticated combination techniques like CCA and KCCA do not work as well in practice as concatenation. We provide theoretical analysis to explain this empirical observation.

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。

↑