arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.08969cs.AIcs.CL
收藏

序列建模中的Meta多任务学习

Meta Multi-Task Learning for Sequence Modeling

Fudan University(复旦大学)

Junkun Chen, Xipeng Qiu, Pengfei Liu, Xuanjing Huang

摘要:

语义组合函数在文本序列的神经表示学习中起着关键作用。尽管他们的成功,大多数现有的模型遭受欠拟合的问题:他们使用相同的共享组合功能的所有位置上的序列,从而缺乏表达能力,由于无法捕捉丰富的组合。此外,不同任务的合成函数是独立的,从零开始学习。在本文中,我们提出了一个新的共享方案的组合功能跨多个任务。具体来说,我们使用一个共享的元网络来捕获语义组合的元知识,并生成特定于任务的语义组合模型的参数。我们对两种类型的任务进行了广泛的实验,文本分类和序列标记,这证明了我们的方法的好处。此外,我们表明,我们提出的模型学习的共享元知识可以被视为现成的知识,很容易转移到新的任务。

英文摘要:

Semantic composition functions have been playing a pivotal role in neural representation learning of text sequences. In spite of their success, most existing models suffer from the underfitting problem: they use the same shared compositional function on all the positions in the sequence, thereby lacking expressive power due to incapacity to capture the richness of compositionality. Besides, the composition functions of different tasks are independent and learned from scratch. In this paper, we propose a new sharing scheme of composition function across multiple tasks. Specifically, we use a shared meta-network to capture the meta-knowledge of semantic composition and generate the parameters of the task-specific semantic composition models. We conduct extensive experiments on two types of tasks, text classification and sequence tagging, which demonstrate the benefits of our approach. Besides, we show that the shared meta-knowledge learned by our proposed model can be regarded as off-the-shelf knowledge and easily transferred to new tasks.

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。

↑