Deep Multitask Learning for Semantic Dependency Parsing

被引：36

作者：

Peng, Hao ^{[1
]}

Thomson, Sam ^{[2
]}

Smith, Noah A. ^{[1
]}

机构：

[1] Univ Washington, Paul G Allen Sch Comp Sci & Engn, Seattle, WA 98195 USA

[2] Carnegie Mellon Univ, Sch Comp Sci, Pittsburgh, PA 15213 USA

来源：

PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 1 | 2017年

关键词：

D O I：

10.18653/v1/P17-1186

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system is able to significantly improve the state of the art for semantic dependency parsing, without using hand-engineered features or syntax. We then explore two multitask learning approaches-one that shares parameters across formalisms, and one that uses higher-order structures to predict the graphs jointly. We find that both approaches improve performance across formalisms on average, achieving a new state of the art. Our code is open-source and available at https://github.com/Noahs-ARK/NeurboParser.

引用

页码：2037 / 2048

页数：12