arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.00166cs.CLcs.AI
收藏

利用对比提示微调使预先训练的语言模型成为端到端的Few-Shot学习者

Making Pre-trained Language Models End-to-end Few-shot Learners with Contrastive Prompt Tuning

Alibaba Group(阿里巴巴集团);Carnegie Mellon University(卡内基梅隆大学);Peking University(北京大学)

Ziyun Xu, Chengyu Wang, Minghui Qiu, Fuli Luo, Runxin Xu, Songfang Huang, Jun Huang

摘要:

预训练的语言模型(PLM)在IR系统中的各种语言理解任务中取得了显著的性能,这些任务需要基于标记的训练数据的微调过程。对于低资源场景,PLM的基于任务的学习利用提示作为任务指导,并将下游任务转化为掩蔽的语言问题,以进行有效的Few-Shot微调。在大多数现有的方法中,基于机器学习的高性能在很大程度上依赖于手工制作的提示和言语化器,这可能会限制这种方法在现实世界场景中的应用。为了解决这个问题,我们提出CP调整,第一个端到端的对比提示微调框架微调PLM没有任何手工工程的任务特定的提示和言语。它集成了任务不变的连续提示编码技术,具有完全可训练的提示参数。我们进一步提出了成对代价敏感的对比学习过程来优化模型,以实现无动词的类映射,并增强提示的任务不变性。它明确地学习区分不同的类,并通过为简单和困难的情况分配不同的成本来使决策边界更平滑。在IR系统和不同PLM中使用的各种语言理解任务的实验表明,CP调整优于最先进的方法。

英文摘要:

Pre-trained Language Models (PLMs) have achieved remarkable performance for various language understanding tasks in IR systems, which require the fine-tuning process based on labeled training data. For low-resource scenarios, prompt-based learning for PLMs exploits prompts as task guidance and turns downstream tasks into masked language problems for effective few-shot fine-tuning. In most existing approaches, the high performance of prompt-based learning heavily relies on handcrafted prompts and verbalizers, which may limit the application of such approaches in real-world scenarios. To solve this issue, we present CP-Tuning, the first end-to-end Contrastive Prompt Tuning framework for fine-tuning PLMs without any manual engineering of task-specific prompts and verbalizers. It is integrated with the task-invariant continuous prompt encoding technique with fully trainable prompt parameters. We further propose the pair-wise cost-sensitive contrastive learning procedure to optimize the model in order to achieve verbalizer-free class mapping and enhance the task-invariance of prompts. It explicitly learns to distinguish different classes and makes the decision boundary smoother by assigning different costs to easy and hard cases. Experiments over a variety of language understanding tasks used in IR systems and different PLMs show that CP-Tuning outperforms state-of-the-art methods.

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。

↑