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 1908.09659cs.CL
收藏

使用弱标记数据学习低资源名称标记

Low-Resource Name Tagging Learned with Weakly Labeled Data

National University of Singapore(新加坡国立大学);Tsinghua University(清华大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Yixin Cao, Zikun Hu, Tat-Seng Chua, Zhiyuan Liu, Heng Ji

摘要:

低资源语言或域中的名称标记遭受不充分的训练数据。现有的工作严重依赖于额外的信息,而留下那些在网络上广泛存在的嘈杂的注释。在本文中,我们提出了一种新的神经模型的名称标记仅基于弱标记(WL)的数据,使其可以应用于任何低资源设置。为了充分利用所有WL语句,我们将它们分为高质量和噪声部分,分别用于两个模块:(1)分类模块专注于大部分噪声数据,可以通过捕获文本上下文语义来有效和鲁棒地预训练标签分类器;以及(2)集中于高质量数据的昂贵的序列标记模块利用具有非实体采样的部分CRF来实现全局最优。两个模块通过共享参数组合。涉及五种低资源语言和细粒度食物域的广泛实验证明了我们的卓越性能(平均6%和7.8%F1增益)以及效率。

英文摘要:

Name tagging in low-resource languages or domains suffers from inadequate training data. Existing work heavily relies on additional information, while leaving those noisy annotations unexplored that extensively exist on the web. In this paper, we propose a novel neural model for name tagging solely based on weakly labeled (WL) data, so that it can be applied in any low-resource settings. To take the best advantage of all WL sentences, we split them into high-quality and noisy portions for two modules, respectively: (1) a classification module focusing on the large portion of noisy data can efficiently and robustly pretrain the tag classifier by capturing textual context semantics; and (2) a costly sequence labeling module focusing on high-quality data utilizes Partial-CRFs with non-entity sampling to achieve global optimum. Two modules are combined via shared parameters. Extensive experiments involving five low-resource languages and fine-grained food domain demonstrate our superior performance (6% and 7.8% F1 gains on average) as well as efficiency.

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。

↑