Exploiting Multi-typed Treebanks for Parsing with Deep Multi-task Learning

2016/06/03 by Jiang Guo, Guo, Jiang, Wanxiang Che +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text and Document Classification Technologies #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1606.01161

openalex publication_date 2016/06/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Various treebanks have been released for dependency parsing. Despite that treebanks may belong to different languages or have different annotation schemes, they contain syntactic knowledge that is potential to benefit each other. This paper presents an universal framework for exploiting these multi-typed treebanks to improve parsing with deep multi-task learning. We consider two kinds of treebanks as source: the multilingual universal treebanks and the monolingual heterogeneous treebanks. Multiple treebanks are trained jointly and interacted with multi-level parameter sharing. Experiments on several benchmark datasets in various languages demonstrate that our approach can make effective use of arbitrary source treebanks to improve target parsing models.

Citations

• Structured Training for Neural Network Transition-Based Parsing

Related

• Parser Training with Heterogeneous Treebanks
• Cross-lingual Universal Dependency Parsing Only from One Monolingual Treebank
• 82 Treebanks, 34 Models: Universal Dependency Parsing with\n Multi-Treebank Models
• Many Languages, One Parser
• Cross-lingual Parsing with Polyglot Training and Multi-treebank\n Learning: A Faroese Case Study