Huizhen Wang

Huizhen Wang

Auto-generated profile, based on publicly available information

Huizhen Wang

Northeastern University

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2009
Verified
Conference Paper
Closed access
FRFeiliang Ren
Feiliang Ren
MZMuhua Zhu
Muhua Zhu
HWHuizhen Wang
Huizhen Wang
JZJingbo Zhu
Jingbo Zhu

20 September 2023
Verified
Book Chapter
Closed access
PDF file
ZRZhibo Ren
Zhibo Ren
HWHuizhen Wang
Huizhen Wang
MZMuhua Zhu
Muhua Zhu
YWYichao Wang
Yichao Wang
TXTong Xiao
Tong Xiao
JZJingbo Zhu
Jingbo Zhu

19 June 2013 in Natural Language Engineering
Verified
Journal Article
Closed access
PDF file
MZMuhua Zhu
Muhua Zhu
JZJingbo Zhu
Jingbo Zhu
HWHuizhen Wang
Huizhen Wang
Shift-reduce parsing has been studied extensively for diverse grammars due to the simplicity and running efficiency. However, in the field of constituency parsing, shift-reduce parsers lag behind state-of-the-art parsers. In this paper we propose a semi-supervised approach for advancing shift-reduce constituency parsing. First, we apply the uptraining approach (Petrov, S. et al. 2010. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP), Cambridge, MA, USA, pp. 705–713) to improve part-of-speech taggers to provide better part-of-speech tags to subsequent shift-reduce parsers. Second, we enhance shift-reduce parsing models with novel features that are defined on lexical dependency information. Both stages depend on the use of large-scale unlabeled data. Experimental results show that the approach achieves overall improvements of 1.5 percent and 2.1 percent on English and Chinese data respectively. Moreover, the final parsing accuracies reach 90.9 percent and 82.2 percent respectively, which are comparable with the accuracy of state-of-the-art parsers.

31 May 2013 in Language Resources and Evaluation
Verified
Journal Article
Closed access
PDF file
MZMuhua Zhu
Muhua Zhu
JZJingbo Zhu
Jingbo Zhu
HWHuizhen Wang
Huizhen Wang

20 July 2013 in Journal of Software
Verified
Journal Article
Closed access
HWHui-Zhen Wang
Hui-Zhen Wang
JZJing-Bo Zhu
Jing-Bo Zhu

8 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
BLBei Li
Bei Li
ZWZiyang Wang
Ziyang Wang
HLHui Liu
Hui Liu
YJYufan Jiang
Yufan Jiang
QDQuan Du
Quan Du
JZJingbo Zhu
Jingbo Zhu
Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but training an extremely deep encoder is time consuming. Moreover, why deep models help NMT is an open question. In this paper, we investigate the behavior of a well-tuned deep Transformer system. We find that stacking layers is helpful in improving the representation ability of NMT models and adjacent layers perform similarly. This inspires us to develop a shallow-to-deep training method that learns deep models by stacking shallow models. In this way, we successfully train a Transformer system with a 54-layer encoder. Experimental results on WMT'16 English-German and WMT'14 English-French translation tasks show that it is $1.4$ $\times$ faster than training from scratch, and achieves a BLEU score of $30.33$ and $43.29$ on two tasks. The code is publicly available at https://github.com/libeineu/SDT-Training/.