Tiejun Zhao

Tiejun Zhao

Auto-generated profile, based on publicly available information

Tiejun Zhao

Harbin Institute of Technology

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

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

Representative Publications

View All Publications
23 October 2022
Verified
Book Chapter
Closed access
PDF file
MZMohan Zhou
Mohan Zhou
YBYalong Bai
Yalong Bai
WZWei Zhang
Wei Zhang
TYTing Yao
Ting Yao
TZTiejun Zhao
Tiejun Zhao
TMTao Mei
Tao Mei

27 January 2020 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
MYMuyun Yang
Muyun Yang
SLShujie Liu
Shujie Liu
KCKehai Chen
Kehai Chen
HZHongyang Zhang
Hongyang Zhang
EZEnbo Zhao
Enbo Zhao
TZTiejun Zhao
Tiejun Zhao
Rare words are usually replaced with a single token in the current encoder-decoder style of neural machine translation, challenging the translation modeling by an obscured context. In this paper, we propose to build a fuzzy semantic representation method for rare words through a hierarchical clustering method to group rare words together, and integrate it into the encoder-decoder framework. This hierarchical structure can compensate the semantic information in both source and target sides, and providing fuzzy context information to capture the semantic of rare words. The introduced fuzzy semantic representation can also alleviate the data sparseness, which is the bottleneck in dealing with rare words in neural machine translation. In particular, our method is easily extended to the Transformer-based NMT model, and learns the fuzzy semantic representation of all in-vocabulary words to enhance sentence representations in addition to rare words. Our experiments on Chinese-to-English translation tasks confirm a significant improvement in the translation quality brought by the proposed method.

23 August 2019 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
KCKehai Chen
Kehai Chen
RWRui Wang
Rui Wang
MUMasao Utiyama
Masao Utiyama
ESEiichiro Sumita
Eiichiro Sumita
TZTiejun Zhao
Tiejun Zhao
Traditional neural machine translation (NMT) methods use the word-level context to predict target language translation while neglecting the sentence-level context, which has been shown to be beneficial for translation prediction in statistical machine translation. This paper represents the sentence-level context as latent topic representations by using a convolution neural network, and designs a topic attention to integrate source sentence-level topic context information into both attention-based and Transformer-based NMT. In particular, our method can improve the performance of NMT by modeling source topics and translations jointly. Experiments on the large-scale LDC Chineseto-English translation tasks and WMT'14 English-to-German translation tasks show that the proposed approach can achieve significant improvements compared with baseline systems.

6 December 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
RJRuili Jiang
Ruili Jiang
KCKehai Chen
Kehai Chen
Xuefeng BaiXuefeng Bai
Xuefeng Bai
ZHZhixuan He
Zhixuan He
JLJuntao Li
Juntao Li
Min ZhangMin Zhang
Min Zhang
The recent surge in versatile large language models (LLMs) demonstrates remarkable success across a wide range of contexts. A key factor contributing to this success is LLM alignment, in which human preference learning plays a decisive role in steering the models’ capabilities toward fulfilling human objectives. In this survey, we review the progress in human preference learning within a unified framework, aiming to provide a comprehensive perspective on established methodologies while exploring avenues to further advance LLM alignment. Specifically, we categorize human preference feedback based on data sources and formats, summarize techniques for human preference modeling and usage, and present an overview of prevailing evaluation protocols for LLM alignment. Finally, we discuss the existing challenges and identify potential directions for future research, with a particular emphasis on generalizability, transferability, and controllability.

8 October 2023
Verified
Book Chapter
Closed access
PDF file
HHHui Huang
Hui Huang
SWShuangzhi Wu
Shuangzhi Wu
XLXinnian Liang
Xinnian Liang
BWBing Wang
Bing Wang
YSYanrui Shi
Yanrui Shi
TZTiejun Zhao
Tiejun Zhao

20 March 2020 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
HSHaipeng Sun
Haipeng Sun
RWRui Wang
Rui Wang
KCKehai Chen
Kehai Chen
MUMasao Utiyama
Masao Utiyama
ESEiichiro Sumita
Eiichiro Sumita
TZTiejun Zhao
Tiejun Zhao
Unsupervised cross-lingual language representation initialization methods such as unsupervised bilingual word embedding (UBWE) pre-training and cross-lingual masked language model (CMLM) pre-training, together with mechanisms such as denoising and back-translation, have advanced unsupervised neural machine translation (UNMT), which has achieved impressive results on several language pairs, particularly French-English and German-English. Typically, UBWE focuses on initializing the word embedding layer in the encoder and decoder of UNMT, whereas the CMLM focuses on initializing the entire encoder and decoder of UNMT. However, UBWE/CMLM training and UNMT training are independent, which makes it difficult to assess how the quality of UBWE/CMLM affects the performance of UNMT during UNMT training. In this paper, we first empirically explore relationships between UNMT and UBWE/CMLM. The empirical results demonstrate that the performance of UBWE and CMLM has a significant influence on the performance of UNMT. Motivated by this, we propose a novel UNMT structure with cross-lingual language representation agreement to capture the interaction between UBWE/CMLM and UNMT during UNMT training. Experimental results on several language pairs demonstrate that the proposed UNMT models improve significantly over the corresponding state-of-the-art UNMT baselines.