Muhua Zhu

Muhua Zhu

Auto-generated profile, based on publicly available information

Muhua Zhu

Alibaba Group

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
9 August 2018 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
QLQiang Li
Qiang Li
DWDerek F. Wong
Derek F. Wong
LCLidia S. Chao
Lidia S. Chao
MZMuhua Zhu
Muhua Zhu
TXTong Xiao
Tong Xiao
MZMin Zhang
Min Zhang
Recently, researchers have shown an increasing interest in incorporating linguistic knowledge into neural machine translation (NMT). To this end, previous works choose either to alter the architecture of NMT encoder to incorporate syntactic information into the translation model, or to generalize the embedding layer of the encoder to encode additional linguistic features. The former approach mainly focuses on injecting the syntactic structure of the source sentence into the encoding process, leading to a complicated model that lacks the flexibility to incorporate other types of knowledge. The latter extends word embeddings by considering additional linguistic knowledge as features to enrich the word representation. It thus does not explicitly balance the contribution from word embeddings and the contribution from additional linguistic knowledge. To address these limitations, this paper proposes a knowledge-aware NMT approach that models additional linguistic features in parallel to the word feature. The core idea is that we propose modeling a series of linguistic features at the word level (knowledge block) using a recurrent neural network (RNN). And in sentence level, those word-corresponding feature blocks are further encoded using a RNN encoder. In decoding, we propose a knowledge gate and an attention gate to dynamically control the proportions of information contributing to the generation of target words from different sources. Extensive experiments show that our approach is capable of better accounting for importance of additional linguistic, and we observe significant improvements from 1.0 to 2.3 BLEU points on Chinese $\leftrightarrow$ English and English $\rightarrow$ German translation tasks.

1 August 2019
Verified
Conference Paper
Open access
DGDongLai Ge
DongLai Ge
JLJunhui Li
Junhui Li
MZMuhua Zhu
Muhua Zhu
SLShoushan Li
Shoushan Li
Sequence-to-sequence (seq2seq) approaches formalize Abstract Meaning Representation (AMR) parsing as a translation task from a source sentence to a target AMR graph. However, previous studies generally model a source sentence as a word sequence but ignore the inherent syntactic and semantic information in the sentence. In this paper, we propose two effective approaches to explicitly modeling source syntax and semantics into neural seq2seq AMR parsing. The first approach linearizes source syntactic and semantic structure into a mixed sequence of words, syntactic labels, and semantic labels, while in the second approach we propose a syntactic and semantic structure-aware encoding scheme through a self-attentive model to explicitly capture syntactic and semantic relations between words. Experimental results on an English benchmark dataset show that our two approaches achieve significant improvement of 3.1% and 3.4% F1 scores over a strong seq2seq baseline.

1 January 2020
Verified
Conference Paper
Open access
PDF file
NDNing Ding
Ning Ding
DLDingkun Long
Dingkun Long
GXGuangwei Xu
Guangwei Xu
MZMuhua Zhu
Muhua Zhu
PXPengjun Xie
Pengjun Xie
Hai-Tao ZhengHai-Tao Zheng
Hai-Tao Zheng
Ning Ding, Dingkun Long, Guangwei Xu, Muhua Zhu, Pengjun Xie, Xiaobin Wang, Haitao Zheng. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.

1 January 2015
Verified
Conference Paper
Open access
JZJingbo Zhu
Jingbo Zhu
MZMuhua Zhu
Muhua Zhu
QWQiang Wang
Qiang Wang
TXTong Xiao
Tong Xiao

17 May 2023 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
ZLZhidong Liu
Zhidong Liu
JLJunhui Li
Junhui Li
MZMuhua Zhu
Muhua Zhu
In neural machine translation (NMT), most sequence-to-sequence (seq2seq) models are trained only with the teacher-forcing paradigm, where the ground truth history is used to predict the next ground truth word. At the inference stage, however, the decoder predicts the next token solely based on history generated from scratch. Both using ground truth history and predicting ground truth words potentially lead to exposure bias. On the one hand, to alleviate the issue of exposure bias caused by using ground truth history, we propose contextual augmentation by allowing substitution, insertion, and deletion of words. The contextual augmentation applies to target sequence to generate non-ground truth and natural history when predicting next words. On the other hand, to alleviate the exposure bias caused by predicting ground truth words, we further apply self distillation to guide the model to carry out optimization according to smoothed prediction distribution, i.e, enable the model to predict not only ground truth words, but also other potentially correct and reasonable words. Experimental results on WMT14 English $\leftrightarrow$ German and IWSLT14 German $\rightarrow$ English translation tasks demonstrate that our approach achieves significant improvements over Transformer on standard benchmarks. Detailed experimental analyses further reveal the effectiveness of our proposed approach on improving the translation quality.

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