arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.09092cs.CLcs.AI
收藏

基于搭配学习的序列迁移学习

Transfer Learning for Sequences via Learning to Collocate

Shanghai University of Finance and Economics(上海财经大学);Fudan University(复旦大学)

Wanyun Cui, Guangyu Zheng, Zhiqiang Shen, Sihang Jiang, Wei Wang

摘要:

迁移学习的目的是通过应用源域的信息来解决目标域的数据稀疏性。给定一个序列(例如一个自然语言句子),通常由递归神经网络(RNN)实现的迁移学习表示顺序的信息传递。RNN使用一系列重复单元来对序列数据进行建模。然而,以往的基于神经网络的迁移学习研究只是简单地用单个向量表示整个句子,这对于seq2seq和序列标记是不可行的。同时,这种逐层迁移学习机制丢失了来自源域的细粒度单元级信息。在本文中,我们提出了对齐的递归传输,ART,实现细胞级的信息传输。抗逆转录病毒疗法是在预培训框架下进行的。每个细胞都专注地接受来自源域中一组位置的传输信息。因此,ART学习跨域词语搭配的方式更加灵活。我们对序列标记任务(词性标注,NER)和句子分类(情感分析)进行了广泛的实验。ART优于所有实验的最新技术。

英文摘要:

Transfer learning aims to solve the data sparsity for a target domain by applying information of the source domain. Given a sequence (e.g. a natural language sentence), the transfer learning, usually enabled by recurrent neural network (RNN), represents the sequential information transfer. RNN uses a chain of repeating cells to model the sequence data. However, previous studies of neural network based transfer learning simply represents the whole sentence by a single vector, which is unfeasible for seq2seq and sequence labeling. Meanwhile, such layer-wise transfer learning mechanisms lose the fine-grained cell-level information from the source domain. In this paper, we proposed the aligned recurrent transfer, ART, to achieve cell-level information transfer. ART is under the pre-training framework. Each cell attentively accepts transferred information from a set of positions in the source domain. Therefore, ART learns the cross-domain word collocations in a more flexible way. We conducted extensive experiments on both sequence labeling tasks (POS tagging, NER) and sentence classification (sentiment analysis). ART outperforms the state-of-the-arts over all experiments.

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。

↑