Weihua Luo

Weihua Luo

Auto-generated profile, based on publicly available information

Weihua Luo

Alibaba Cloud Computing, Hangzhou, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
1 January 2021
Verified
Conference Paper
Open access
PDF file
JZJinpeng Zhang
Jinpeng Zhang
BJBaijun Ji
Baijun Ji
NXNini Xiao
Nini Xiao
XDxiangyu Xiang Duan
xiangyu Xiang Duan
ZDZhengmin Duan
Zhengmin Duan
WLWeihua Luo
Weihua Luo
Jinpeng Zhang, Baijun Ji, Nini Xiao, Xiangyu Duan, Min Zhang, Yangbin Shi, Weihua Luo. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021.

26 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
LYLiang Yao
Liang Yao
BYBaosong Yang
Baosong Yang
HZHaibo Zhang
Haibo Zhang
WLWeihua Luo
Weihua Luo
BCBoxing Chen
Boxing Chen
As a crucial role in cross-language information retrieval (CLIR), query translation has three main challenges: 1) the adequacy of translation; 2) the lack of in-domain parallel training data; and 3) the requisite of low latency. To this end, existing CLIR systems mainly exploit statistical-based machine translation (SMT) rather than the advanced neural machine translation (NMT), limiting the further improvements on both translation and retrieval quality. In this paper, we investigate how to exploit neural query translation model into CLIR system. Specifically, we propose a novel data augmentation method that extracts query translation pairs according to user clickthrough data, thus to alleviate the problem of domain-adaptation in NMT. Then, we introduce an asynchronous strategy which is able to leverage the advantages of the real-time in SMT and the veracity in NMT. Experimental results reveal that the proposed approach yields better retrieval quality than strong baselines and can be well applied into a real-world CLIR system, i.e. Aliexpress e-Commerce search engine. Readers can examine and test their cases on our website: https://aliexpress.com .

26 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
TBTianchi Bi
Tianchi Bi
LYLiang Yao
Liang Yao
BYBaosong Yang
Baosong Yang
HZHaibo Zhang
Haibo Zhang
WLWeihua Luo
Weihua Luo
BCBoxing Chen
Boxing Chen
Query translation (QT) is a key component in cross-lingual information retrieval system (CLIR). With the help of deep learning, neural machine translation (NMT) has shown promising results on various tasks. However, NMT is generally trained with large-scale out-of-domain data rather than in-domain query translation pairs. Besides, the translation model lacks a mechanism at the inference time to guarantee the generated words to match the search index. The two shortages of QT result in readable texts for human but inadequate candidates for the downstream retrieval task. In this paper, we propose a novel approach to alleviate these problems by limiting the open target vocabulary search space of QT to a set of important words mined from search index database. The constraint translation candidates are employed at both of training and inference time, thus guiding the translation model to learn and generate well performing target queries. The proposed methods are exploited and examined in a real-word CLIR system--Aliexpress e-Commerce search engine. Experimental results demonstrate that our approach yields better performance on both translation quality and retrieval accuracy than the strong NMT baseline.

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
HZHao Zhou
Hao Zhou
ZWZhijun Wang
Zhijun Wang
SHShujian Huang
Shujian Huang
XHXin Huang
Xin Huang
XHXue Han
Xue Han
JCJiajun Chen
Jiajun Chen
Large Language Models (LLMs) are often English-centric due to the disproportionate distribution of languages in their pre-training data. Enhancing non-English language capabilities through post-pretraining often results in catastrophic forgetting of high-resource languages. Previous methods either achieve good expansion with severe forgetting or slight forgetting with poor expansion, indicating the challenge of balancing language expansion while preventing forgetting. In this paper, we propose a method called MoE-LPR (Mixture-of-Experts with Language Priors Routing) to alleviate this problem. MoE-LPR employs a two-stage training approach to enhance the multilingual capability. First, the model is post-pretrained into a Mixture-of-Experts(MoE) architecture by upcycling, where all the original parameters are frozen and new experts are added. In this stage, we focus improving the ability on expanded languages, without using any original language data. Then, the model reviews the knowledge of the original languages with replay data amounting to less than 1% of post-pretraining, where we incorporate language priors routing to better recover the abilities of the original languages. Evaluations on multiple benchmarks show that MoE-LPR outperforms other post-pretraining methods. Freezing original parameters preserves original language knowledge while adding new experts preserves the learning ability. Reviewing with LPR enables effective utilization of multilingual knowledge within the parameters. Additionally, the MoE architecture maintains the same inference overhead while increasing total model parameters. Extensive experiments demonstrate MoE-LPR’s effectiveness in improving expanded languages and preserving original language proficiency with superior scalability.

1 January 2025
Verified
Conference Paper
Open access
PDF file
HYHuifeng Yin
Huifeng Yin
YZYu Zhao
Yu Zhao
MWMinghao Wu
Minghao Wu
XNXuanfan Ni
Xuanfan Ni
BZBo Zeng
Bo Zeng
KZKaifu Zhang
Kaifu Zhang
Huifeng Yin, Yu Zhao, Minghao Wu, Xuanfan Ni, Bo Zeng, Hao Wang, Tianqi Shi, Liangying Shao, Chenyang Lyu, Longyue Wang, Weihua Luo, Kaifu Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

23 December 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
DSDan Song
Dan Song
XZXuanpu Zhang
Xuanpu Zhang
JZJianhao Zeng
Jianhao Zeng
PZPengxin Zhan
Pengxin Zhan
QCQingguo Chen
Qingguo Chen
ALAnan Liu
Anan Liu
Image-based virtual try-on aims to transfer target in-shop clothing to a dressed model image, the objectives of which are totally taking off original clothing while preserving the contents outside of the try-on area, naturally wearing target clothing and correctly inpainting the gap between target clothing and original clothing. Tremendous efforts have been made to facilitate this popular research area, but cannot keep the type of target clothing with the try-on area affected by original clothing. In this paper, we focus on the unpaired virtual try-on situation where target clothing and original clothing on the model are different, i.e., the practical scenario. To break the correlation between the try-on area and the original clothing and make the model learn the correct information to inpaint, we propose an adaptive mask training paradigm that dynamically adjusts training masks. It not only improves the alignment and fit of clothing but also significantly enhances the fidelity of virtual try-on experience. Furthermore, we for the first time propose two metrics for unpaired try-on evaluation, the Semantic-Densepose-Ratio (SDR) and Skeleton-LPIPS (S-LPIPS), to evaluate the correctness of clothing type and the accuracy of clothing texture. For unpaired try-on validation, we construct a comprehensive cross-try-on benchmark (Cross-27) with distinctive clothing items and model physiques, covering a broad try-on scenarios. Experiments demonstrate the effectiveness of the proposed methods, contributing to the advancement of virtual try-on technology and offering new insights and tools for future research in the field. The code, model and benchmark will be publicly released.