DeepAI AI Chat
Log In Sign Up

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

by   Jiang Guo, et al.
Harbin Institute of Technology
Baidu, Inc.

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.


page 1

page 2

page 3

page 4


Open-Domain Frame Semantic Parsing Using Transformers

Frame semantic parsing is a complex problem which includes multiple unde...

Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning

Large multilingual pretrained language models such as mBERT and XLM-RoBE...

Cross-lingual Parsing with Polyglot Training and Multi-treebank Learning: A Faroese Case Study

Cross-lingual dependency parsing involves transferring syntactic knowled...

Towards Language-Universal End-to-End Speech Recognition

Building speech recognizers in multiple languages typically involves rep...

Sequential Sentence Classification in Research Papers using Cross-Domain Multi-Task Learning

The task of sequential sentence classification enables the semantic stru...

UDapter: Language Adaptation for Truly Universal Dependency Parsing

Recent advances in the field of multilingual dependency parsing have bro...

A Novel Multi-Task Learning Approach for Context-Sensitive Compound Type Identification in Sanskrit

The phenomenon of compounding is ubiquitous in Sanskrit. It serves for a...