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 1702.02535cs.CL
收藏

基于分组权重共享的领域知识挖掘及其在文本分类中的应用

Exploiting Domain Knowledge via Grouped Weight Sharing with Application to Text Categorization

University of Texas at Austin(德克萨斯大学奥斯汀分校);Northeastern University(东北大学)

Ye Zhang, Matthew Lease, Byron C. Wallace

摘要:

NLP神经模型的一个基本优势是它们能够从头开始学习表示。然而,在实践中,这往往意味着忽视现有的外部语言资源,例如,WordNet或领域特定本体,如统一医学语言系统(UMLS)。我们提出了一种通过权重共享来利用此类资源的通用、新颖方法。在神经网络中的权值共享的先前工作主要将其视为模型压缩的手段。相比之下,我们将权重共享视为将先验知识纳入神经模型的灵活机制。我们表明,这种方法始终产生改进的分类任务的性能相比,基线策略,不利用权重共享。

英文摘要:

A fundamental advantage of neural models for NLP is their ability to learn representations from scratch. However, in practice this often means ignoring existing external linguistic resources, e.g., WordNet or domain specific ontologies such as the Unified Medical Language System (UMLS). We propose a general, novel method for exploiting such resources via weight sharing. Prior work on weight sharing in neural networks has considered it largely as a means of model compression. In contrast, we treat weight sharing as a flexible mechanism for incorporating prior knowledge into neural models. We show that this approach consistently yields improved performance on classification tasks compared to baseline strategies that do not exploit weight sharing.

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。

↑