arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2210.12435cs.CL
收藏

关系分类的生成式提示微调

Generative Prompt Tuning for Relation Classification

Beijing University of Posts and Telecommunications(北京邮电大学);Singapore University of Technology and Design(新加坡科技设计大学)

Jiale Han, Shuai Zhao, Bo Cheng, Shengkun Ma, Wei Lu

摘要:

使用提示来探索包含在用于下游任务的预训练语言模型中的知识现在已经成为一个活跃的话题。目前的提示微调方法大多通过添加完形填空式短语并将所有标签映射为固定长度的动词化来将下游任务转换为掩蔽语言建模问题,这对于具有简单标签空间的任务是有效的。然而,当应用于呈现复杂标签空间的关系分类时,香草提示微调方法可能会由于严格的提示限制而难以处理具有任意长度的标签动词化。受预训练生成模型的文本填充任务的启发,可以灵活地预测缺失的跨度,我们提出了一种新的生成提示微调方法,将关系分类重新定义为填充问题,这使我们的方法摆脱了当前基于提示的方法的局限性,从而充分利用了实体和关系类型的丰富语义。此外,我们设计了实体引导的解码和判别关系评分,以在推理过程中有效和高效地生成和对齐关系。在完全监督设置和低资源设置下的广泛实验证明了我们的方法的有效性。

英文摘要:

Using prompts to explore the knowledge contained within pre-trained language models for downstream tasks has now become an active topic. Current prompt tuning methods mostly convert the downstream tasks to masked language modeling problems by adding cloze-style phrases and mapping all labels to verbalizations with fixed length, which has proven effective for tasks with simple label spaces. However, when applied to relation classification exhibiting complex label spaces, vanilla prompt tuning methods may struggle with label verbalizations with arbitrary lengths due to rigid prompt restrictions. Inspired by the text infilling task for pre-training generative models that can flexibly predict missing spans, we propose a novel generative prompt tuning method to reformulate relation classification as an infilling problem, which frees our approach from limitations of current prompt based approaches and thus fully exploits rich semantics of entity and relation types. In addition, we design entity-guided decoding and discriminative relation scoring to generate and align relations effectively and efficiently during inference. Extensive experiments under fully supervised settings and low-resource settings demonstrate the effectiveness of our approach.

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。

↑