Incorporating target language semantic roles into a string-to-tree translation model
| ||||||||||||||
Chao Su, Yu-hang Guo, He-yan Huang, Shu-min Shi, Chong Feng. Incorporating target language semantic roles into a string-to-tree translation model[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(10): 1534-1542.
@article{title="Incorporating target language semantic roles into a string-to-tree translation model",
author="Chao Su, Yu-hang Guo, He-yan Huang, Shu-min Shi, Chong Feng",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="18",
number="10",
pages="1534-1542",
year="2017",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1601349"
}
%0 Journal Article
%T Incorporating target language semantic roles into a string-to-tree translation model
%A Chao Su
%A Yu-hang Guo
%A He-yan Huang
%A Shu-min Shi
%A Chong Feng
%J Frontiers of Information Technology & Electronic Engineering
%V 18
%N 10
%P 1534-1542
%@ 2095-9184
%D 2017
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1601349
TY - JOUR
T1 - Incorporating target language semantic roles into a string-to-tree translation model
A1 - Chao Su
A1 - Yu-hang Guo
A1 - He-yan Huang
A1 - Shu-min Shi
A1 - Chong Feng
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 18
IS - 10
SP - 1534
EP - 1542
%@ 2095-9184
Y1 - 2017
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1601349
Abstract: The string-to-tree model is one of the most successful syntax-based statistical machine translation (SMT) models. It models the grammaticality of the output via target-side syntax. However, it does not use any semantic information and tends to produce translations containing semantic role confusions and error chunk sequences. In this paper, we propose two methods to use semantic roles to improve the performance of the string-to-tree translation model: (1) adding role labels in the syntax tree; (2) constructing a semantic role tree, and then incorporating the syntax information into it. We then perform string-to-tree machine translation using the newly generated trees. Our methods enable the system to train and choose better translation rules using semantic information. Our experiments showed significant improvements over the state-of-the-art string-to-tree translation system on both spoken and news corpora, and the two proposed methods surpass the phrase-based system on large-scale training data.
Full Text:
<3945>
Summary: 
<2720>
CLC number: TP391
On-line Access: 2024-08-27
Received: 2023-10-17
Revision Accepted: 2024-05-08
Crosschecked: 2017-11-03
Cited: 0
Clicked: 8724
Open peer comments: Debate/Discuss/Question/Opinion
<1>