An Empirical Study of Encoders and Decoders in Graph-Based Dependency Parsing
Graph-based dependency parsing consists of two steps: first, an encoder produces a feature representation for each parsing substructure of the input sentence, which is then used to compute a score for the substructure; and second, a decoder finds the parse tree whose substructures have the largest t...
Main Authors: | Ge Wang, Ziyuan Hu, Zechuan Hu, Kewei Tu |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8999592/ |
Similar Items
-
From POS tagging to dependency parsing for biomedical event extraction
by: Dat Quoc Nguyen, et al.
Published: (2019-02-01) -
A Computer Language Transformation System Capable of Generalized Context-Dependent Parsing
by: Thurston, Adrian
Published: (2008) -
Robust Dependency Parsing of Spontaneous Japanese Spoken Language
by: Ohno, Tomohiro, et al.
Published: (2005) -
Learning for semantic parsing using statistical syntactic parsing techniques
by: Ge, Ruifang
Published: (2014) -
Increasing NLP Parsing Efficiency with Chunking
by: Mark Dáibhidh Anderson, et al.
Published: (2018-09-01)