Shu Jiang

Shu Jiang

Auto-generated profile, based on publicly available information

Shu Jiang

Nantong University

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
16 January 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
MKMUHAMMAD JABIR KHAN
MUHAMMAD JABIR KHAN
Weiping DingWeiping Ding
Weiping Ding
SJShu Jiang
Shu Jiang
MAMuhammad Akram
Muhammad Akram

26 May 2021 in IEEE Access
Verified
Journal Article
Open access
SJShu Jiang
Shu Jiang
ZZZhuosheng Zhang
Zhuosheng Zhang
HZHai Zhao
Hai Zhao
JLJiangtong Li
Jiangtong Li
YYYang Yang
Yang Yang
NXNing Xia
Ning Xia
Simplified Molecular Input Line Entry System (SMILES) provides a text-based encoding method to describe the structure of chemical species and formulize general chemical reactions. Considering that chemical reactions have been represented in a language form, we present a symbol only model to generally predict the yield of organic synthesis reaction without considering complex quantum physical modeling or chemistry knowledge. Our model is the first deep neural network application that treats chemical reaction text segments as embedding representation to the most recent deep natural language processing. Experimental results show our model can effectively predict chemical reactions, which achieves a high accuracy of 99.76% on practicality judgment and the Root Mean Square Error (RMSE) is around 0.2 for yield prediction. Our work shows the great potential for automatic yield prediction for organic reactions under general conditions and further applications in synthesis path prediction with the least modeling cost.

1 January 2021
Verified
Conference Paper
Open access
PDF file
HJHongjiang Jing
Hongjiang Jing
LZLi Zuchao
Li Zuchao
HZHai Zhao
Hai Zhao
SJShu Jiang
Shu Jiang
Hongjiang Jing, Zuchao Li, Hai Zhao, Shu Jiang. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.

1 January 2025 in Research
Verified
Journal Article
Open access
YYYifei Yang
Yifei Yang
RSRunhan Shi
Runhan Shi
LZLi Zuchao
Li Zuchao
SJShu Jiang
Shu Jiang
BLBao-Liang Lu
Bao-Liang Lu
HZHai Zhao
Hai Zhao
Large language models (LLMs) have showcased remarkable capabilities in the realm of AI for Science, and chemistry has greatly benefited from the advancement of AI tools. With a strong capacity for learning sequential data like natural language, LLMs offer immense potential. Despite this promise, the application of LLMs in chemistry remains limited, with few models specifically designed for chemical data and tasks. Hence, we propose leveraging LLMs to comprehensively model both chemical sequences and natural language sequences, aiming to tackle diverse chemical tasks. We introduce BatGPT-Chem, a general foundation large-scale model with 15 billion parameters tailored for chemical engineering. Built on a corpus of over 100 million chemical instances, BatGPT-Chem specializes in 5 core tasks: retrosynthesis prediction, molecule design, molecule description, product inference, and yield prediction. BatGPT-Chem comprehensively models the information flow between chemical language and natural language, enabling full-spectrum prediction across chemical tasks. It is one of the largest bilingual chemistry-specific LLMs, supporting both English and Chinese for input and output. BatGPT-Chem is also the first automated retrosynthesis tool capable of explicitly predicting reaction conditions, a critical but often overlooked aspect in previous models. Through rigorous zero-shot evaluations, BatGPT-Chem demonstrates state-of-the-art performance, surpassing both existing chemical LLMs and general-purpose models in accuracy and validity across a diverse range of tasks. Notably, it demonstrates superior ability in predicting both reactants and reaction conditions, as well as strong generalization in low-data settings. These results suggest that BatGPT-Chem is among the most advanced and practical chemical LLMs, with strong potential to support real-world applications in synthesis planning, drug discovery, and materials design.

9 January 2024 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
SJShu Jiang
Shu Jiang
LZLi Zuchao
Li Zuchao
HZHai Zhao
Hai Zhao
Weiping DingWeiping Ding
Weiping Ding
Entity-relation extraction is the essential information extraction task and can be decomposed into Named Entity Recognition (NER) and Relation Extraction (RE) subtasks. This paper proposes a novel joint entity-relation extraction method that models the entity-relation extraction task as full shallow semantic dependency graph parsing. Specifically, it jointly and simultaneously converts the entities and relation mentions as the edges of the semantic dependency graph to be parsed and their types as the labels. This model also integrates the advantages of multiple feature tagging methods and enriches the token representation. Furthermore, second-order scoring is introduced to exploit the relationships between entities and relations, which improves the model performance. Our work is the first time to fully model entities and relations into a graph and uses higher-order modules to address their interaction problems. Compared with state-of-the-art scores on five benchmarks (ACE04, ACE05, CoNLL04, ADE, and SciERC), empirical results show that our proposed model makes significant improvements and demonstrates its effectiveness and practicability.

8 November 2024 in Information Sciences
Verified
Journal Article
Closed access
Weiping DingWeiping Ding
Weiping Ding
THTao Hou
Tao Hou
JHJiashuang Huang
Jiashuang Huang
HJHengrong Ju
Hengrong Ju
SJShu Jiang
Shu Jiang