Author Image

Hi, I am Tommy

Tommy Chien

PhD student at Renmin University of China

I am Tommy Chien (钱泓锦) (Hongjin Qian), currently a PhD student from Gaoling School of Artificial Intelligence (GSAI), Renmin University of China, working on Natural Language Processing and Information Retrieval, supervised by Prof. Zhicheng Dou and Prof. Ji-Rong Wen. Before enrolling into GSAI, I was an NLP engineer of Beijing Academy of Artificial Intelligence (BAAI) working on QA system. Prior to BAAI, I worked in a start-up AI company Elensdata.

Outside of work, I enjoy jogging, cooking, and playing guitar on a daily basis, as well as seasonal hobbies like snowboarding and golf. I also love traveling and have visited 31 countries and over 280 cities.

Cooking
Photography
Snowboarding
Guitar
Academic
Coding

Education
Renmin University of China
2020-2024
Ph.D student in Artificial Intelligence
Publications
  • Kelong Mao, Hongjin Qian, Fengran Mo, Zhicheng Dou, Bang Liu, Xiaohua Cheng, Zhao Cao. Learning Denoised and Interpretable Session Representation for Conversational Search in [theWebConf 2023] [pdf]
  • Hongjin Qian, Zhicheng Dou. Topic-Enhanced Personalized Retrieval-based Chatbot in [EMNLP 2022] [pdf]
  • Hongjin Qian, Zhicheng Dou. Explicit Query Rewriting for Conversational Dense Retrieval in [EMNLP 2022] [pdf]
  • Kelong Mao, Zhicheng Dou, Hongjin Qian, Fengran Mo, Xiaohua Cheng and Zhao Cao. ConvTrans: Transforming Web Search Sessions for Conversational Dense Retrieval in [EMNLP 2022] [pdf]
  • Hanxun Zhong, Zhicheng Dou, Yutao Zhu, Hongjin Qian, Ji-Rong Wen. Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation in [NAACL 2022] [pdf]
  • Yu Guo, Zhengyi Ma, Jiaxin Mao, Hongjin Qian, Xinyu Zhang, Hao Jiang, Zhao Cao and Zhicheng Dou. Webformer: Pre-training with Web Pages for Information Retrieval in [SIGIR 2022] [pdf]
  • Kelong Mao, Zhicheng Dou and Hongjin Qian. Curriculum Contrastive Context Denoising for Few-shot Conversational Dense Retrieval in [SIGIR 2022] [pdf]
  • Hongjin Qian, Zhicheng Dou, Yutao Zhu, Yueyuan Ma and Ji-Rong Wen. Learning Implicit User Profile for Personalized Retrieval-Based Chatbot in [CIKM 2021] [pdf]
  • Hongjin Qian, Xiaohe Li, Hanxun Zhong, Yu Guo, Yueyuan Ma, Yutao Zhu, Zhanliang Liu, Zhicheng Dou and Ji-Rong Wen. Pchatbot: A Large-Scale Dataset for Personalized Chatbot in [SIGIR 2021 Resource Track] [pdf]
  • Yafei Liu *, Hongjin Qian *, Hengpeng Xu, Jinmao Wei. Speaker or Listener? The Role of a Dialog Agent in [Findings of EMNLP 2020] [pdf]
University of Sydney
2017-2019
Master of Information Technology, Major in Data Management and Analytics
Nankai University
2013-2017
Bachelor of Science, Major in Electronic information Science and Technology

Experiences

1
Research Intern
Poisson Lab, Huawei.

Apr 2022 - Present, Beijing, China

Responsibilities:
  • Pretraining for IR
  • Model-oriented IR
PhD. Researcher
Gaoling School of Artificial Intelligence, Renmin University of China.

Sept 2020 - Present, Beijing, China

Responsibilities:
  • Personalized Chatbot
  • Conversational Information seeking
  • Document Ranking
Patents:
  • A method for retrieval-based personalized chatbot (CN113901188A)
    Zhicheng Dou, Hongjin Qian
2
3
NLP Engineer
Beijing Academy of Artificial Intelligence.

Jun 2020 - Mar 2021, Beijing, China

Beijing Academy of Artificial Intelligence (BAAI) is a non-profit research institute dedicated to promoting collaboration among academia and industries, as well as fostering top talents and a focus on long-term research on the fundamentals of AI technology.

Responsibilities:
  • QA System dedicated in Governance Domain
  • Dense Vector Search
  • Fine-Grained Named Entity Recognition
Patents:
  • A method for long text retrieval in open-domain question answering tasks (CN111881264A)
    Hongjin Qian, Zhanliang Liu, Zhicheng Dou, Jiajun Liu
  • Optical character recognition method incorporating pretrained language model (CN111738251A)
    Hongjin Qian, Zhanliang Liu, Zhicheng Dou, Jiajun Liu
  • A method for Uyghur language Named Entity Recognition (CN111814433A)
    Hongjin Qian, Zhanliang Liu, Zhicheng Dou, Jiajun Liu
  • A semantic parsing method based on rules and learning (CN112347793A)
    Hongjin Qian, Xiaotong Li, Zhanliang Liu, Yushu Yang, Zhicheng Dou, Gang Cao, Ji-Rong Wen
  • A Multi-level long text dense retrieval method (CN112988952A)
    Hongjin Qian, Zhanliang Liu, Zhicheng Dou, Gang Cao, Ji-Rong Wen
  • Multi-source NL2SQL system based on semantic rules and multi-dimensional model (CN112559550A)
    Zhi Li, Hongjin Qian, Zhanliang Liu
  • A method for automatically constructing FAQ knowledge base (CN112784022A)
    Sixu Guo, Hongjin Qian, Yushu Yang, Zhanliang Liu, Zhicheng Dou, Gang Cao, Ji-Rong Wen
  • A method for automatically generating FAQ knowledge base based on complex data format (CN112800177A)
    Sixu Guo, Hongjin Qian, Yushu Yang, Zhanliang Liu, Zhicheng Dou, Gang Cao, Ji-Rong Wen
  • A document-ranking method for text retrieval (CN111930928A)
    Yu Zhang, Hongjin Qian, Zhanliang Liu, Zhicheng Dou
  • A method for extracting text from image document (CN112036406A)
    Yuanyuan Huang, Hongjin Qian, Zhanliang Liu, Zhicheng Dou
  • A semantic retrieval method (CN112035730A)
    Yang Zhou, Hongjin Qian, Zhanliang Liu, Zhicheng Dou
  • A method for quickly realizing NL2SQL based on vectorized semantic rules (CN112001188A)
    Chaofeng Xiao, Zhi Li, Hongjin Qian, Zhanliang Liu, Zhicheng Dou
  • A method for testing interface performance (CN111881060A)
    Huan Zhang, Zhi Li, Hongjin Qian, Zhanliang Liu
  • A method for automatically constructing FAQ knowledge base based on tabular data (CN112800032A)
    Sixu Guo, Yushu Yang, Hongjin Qian, Zhanliang Liu, Zhicheng Dou, Gang Cao, Ji-Rong Wen
NLP Engineer
Elensdata.

Jan 2019 - Sept 2020, Beijing, China

Elensdata is a start-up company which offers high-calibre data science/AI solutions that help real businesses, in media, finance, etc.

Responsibilities:
  • Core NLP Toolkit for Chinese, English and Uyghur
  • NLP Applications in Multiple Domains (Financial, Security, Media etc.)
  • Large-Scale Pretrained Language Model and Text Generation
Patents:
  • A Latin-alphabet-based Uyghur language processing method and system (CN111428509A)
    Hongjin Qian, Zhen Huang, Zhicheng Dou, Zhanliang Liu
  • A method for Pinyin-based Chinese language representation (CN110162789A)
    Zhicheng Dou, Hongjin Qian, Zhen Huang
  • A natural language processing method and system based on index data (CN111488423A)
    Zhanliang Liu, Hongjin Qian, Zhicheng Dou, Jiajun Liu
4

Skills

Achievements

Footprints

Flights

Snowboarding

Sports