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 2009.09568cs.CL
收藏

自然语言理解中用于Few-Shot槽标注的矢量投影网络

Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding

Shanghai Jiao Tong University(上海交通大学)

Su Zhu, Ruisheng Cao, Lu Chen, Kai Yu

摘要:

由于会话对话系统的巨大发展,Few-Shot槽标记变得对快速域转移和适应有吸引力。在本文中,我们提出了一个矢量投影网络的Few-Shot槽标记,利用投影的上下文词嵌入每个目标标签向量作为词标签的相似性。本质上,这种方法相当于具有自适应偏差的归一化线性模型。对比实验表明,我们提出的基于向量投影的相似性度量可以显着优于其他变种。具体来说,在基准SNIPS和NER的五次设置中,我们的方法分别通过F $_1$分数上的$6.30$和$13.79$点优于最强的少样本学习基线。我们的代码将在https://github.com/sz128/few_shot_slot_tagging_and_NER上发布。

英文摘要:

Few-shot slot tagging becomes appealing for rapid domain transfer and adaptation, motivated by the tremendous development of conversational dialogue systems. In this paper, we propose a vector projection network for few-shot slot tagging, which exploits projections of contextual word embeddings on each target label vector as word-label similarities. Essentially, this approach is equivalent to a normalized linear model with an adaptive bias. The contrastive experiment demonstrates that our proposed vector projection based similarity metric can significantly surpass other variants. Specifically, in the five-shot setting on benchmarks SNIPS and NER, our method outperforms the strongest few-shot learning baseline by $6.30$ and $13.79$ points on F$_1$ score, respectively. Our code will be released at https://github.com/sz128/few_shot_slot_tagging_and_NER.

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。

↑