Menu
Home

Zhang, Tianhui (张天慧)

alt text 

PhD student,
Department of Computer Science
University of Liverpool
Liverpool, UK
E-mail: tianhui.zhang@liverpool.ac.uk

About me

I am a second year PhD student at University of Liverpool supervised by Prof Bollegala Danushka and Dr. Bei Peng. Prior to that, I obtained Master degree with Distinction from University College London and Bachelor degree with First Class from University of Liverpool. My main research interests include knowledge graph, commonsense reasoning and text classification. Also, I do some research about text generation. I focus on using AI to solve practical problems.

Research

My research interests include:

  • Natural language processing

  • Knowledge Graph

  • Commonsense Reasoning

Current work

  • Generative Commonsense Reasoning

Papers

  • Title: Learning to Predict Concept Ordering for Common Sense Generation. Tianhui Zhang, Danushka Bollegala and Bei Peng, IJCNLP-AACL, 2023. Read More
  • Title: Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning Tianhui Zhang, Bei Peng and Danushka Bollegala, EMNLP, 2024. Read More
  • Title: BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages. Shamsuddeen Hassan Muhammad et ;al., ACL, 2025. Read More
  • Title: Evaluating the Evaluation of Diversity in Commonsense Generation Tianhui Zhang, Bei Peng and Danushka Bollegala, ACL, 2025.

Projects

  1. Companies Knowledge graph construction 05.2022-09.2022

    • Design the schema of the knowledge graph

    • Crawled the company information from websites

    • Develop algorithms to fetch the inference chains

  2. Financial Open Information extraction, 06.2020-08.2022

    • Construct knowledge graph by designing a BERT open information extraction system.

    • Create the dataset from Wikipedia and SEC filings

  3. Abstract Summarization, 02.2020-04.2020

    • Applying 3 pre-trained model (BERT, MASS and MiniLM) on abstract summarization task and compared the performance on WikiHow dataset

  4. Negative transfer of word meta-embedding, 01.2019-08.2019

    • Research on negative transfer of word embedding under supervision of Prof. D. Bollegala to find better performance

    • Show great performance on tasks such as semantic similarity

  5. Search Filter, 02.2018-05.2018

    • Developing a website could answer user's questions by Crawled webpages

    • TextRank algorithm and cosine similarity to rand the paragraphs and webpages

Education

PhD student, University of Liverpool, United Kingdom, 2022-

MSC Data Science and Machine Learning, University College London, United Kingdom, 09.2019-12.2020

  • Distinction Degree, 75% Average score

BSC Artificial Intelligence, University of Liverpool, United Kingdom, 09.2015-01.2019

  • First Class Degree

Activities

  1. Teaching Assistant, University of Liverpool, 2022-2023

    • COMP337/527 Data Mining and Visualization 2023

    • COMP304 Knowledge Representation 2022/2023

    • COMP518 Database and Information System 2023

Internship experience

  1. Knowledge graph developer, IICT, Suzhou, 01.2022-09.2022

    • Research the newest natural laguage processing algorithms and knowledge graph on hot news and company information

    • Construct and maintain a finance knowledge graph

    • Tracked, studied, reproduced, and improved up-to-date machine learning methods

  2. Webpage developer, market department, Xi'an Jiaotong Liverpool University, 08.2019-06.2021

    • Implemented and maintain a market customer analysis website.

    • Help staff to analyze customer's preferences with their job, province and university.

  3. Software Engineer, RISE English School, 06.2017-09.2017

    • Develop a system to manage the students and classes

    • Help teachers to easily track their students’ courses, classes and tuition fee

    • Update the information automatically in the database and generate the report weekly


A brief cv.