Maths is Beautiful

Shenbin Qian

Centre for Translation Studies

14LC03, Library Building

University of Surrey

Bio

I am a third-year PhD student (started in Jan 2022) from the Centre for Translation Studies, University of Surrey, where I work on the improvement and evaluation of machine translation for user-generated content using deep learning methods. I am advised by Prof Constantin Orasan, Dr Félix do Carmo and Dr Diptesh Kanojia.

I was a linguist in second language acquisition and translation studies during my undergraduate years. Later, I self-taught programming after joining a technology company. I started applying statistical and deep learning methods to language and vision during my post-graduate study. Now, I am interested in how machines learn language, vision and acoustic.

Education

  • MSc in Applied Data Science and Statistics, 2022
  • University of Exeter, UK

  • MA in Translation and Interpreting, 2017
  • Xihua University, China

Interest

Machine Translation Sentiment Analysis Sequence Labeling Application of Large Language Models

Follow Me

Publications

What do Large Language Models Need for Machine Translation Evaluation?

Shenbin Qian, Archchana Sindhujan, Minnie Kabra, Diptesh Kanojia, Constantin Orăsan, Tharindu Ranasinghe, Fred Blain

Accepted by the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP2024 Main)

A Multi-task Learning Framework for Evaluating Machine Translation of Emotion-loaded User-generated Content

Shenbin Qian, Constantin Orăsan, Diptesh Kanojia, Félix do Carmo

Accepted by the Ninth Conference on Machine Translation (WMT24)

Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content?

Shenbin Qian, Constantin Orăsan, Diptesh Kanojia, Félix do Carmo

Accepted by the 11th Workshop on Asian Translation (WAT2024)

Evaluating Machine Translation for Emotion-loaded User Generated Content (TransEval4Emo-UGC)

Shenbin Qian, Constantin Orăsan, Félix do Carmo, Diptesh Kanojia

Proceedings of the 25th Annual Conference of the European Association for Machine Translation (EAMT2024)

Character-level language models for abbreviation and long-form detection.

Leonardo Zilio*, Shenbin Qian*, Diptesh Kanojia, Constantin Orăsan

Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Challenges of Human vs Machine Translation of Emotion-Loaded Chinese Microblog Texts.

Shenbin Qian, Constantin Orăsan, Félix do Carmo, Diptesh Kanojia

Proceedings of the Machine Translation Summit XIX, Vol. 2: User Track (MTSUMMIT XIX)

Evaluation of Chinese-English Machine Translation of Emotion-Loaded Microblog Texts: A Human Annotated Dataset for the Quality Assessment of Emotion Translation.

Shenbin Qian, Constantin Orăsan, Félix do Carmo, Qiuliang Li, Diptesh Kanojia

Proceedings of the 24th Annual Conference of the European Association for Machine Translation (EAMT2023)

SURREY-CTS-NLP at WASSA2022: An Experiment of Discourse and Sentiment Analysis for the Prediction of Empathy, Distress and Emotion.

Shenbin Qian, Constantin Orăsan, Diptesh Kanojia, Hadeel Saadany, Félix do Carmo

Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA2022)

Research Projects

University of Surrey's SME Innovation Voucher Scheme

Mar, 2022 - Jun, 2022

Led by Prof Constantin Orasan, collaborated with Monaco Solicitors (MS), this project investigated ways in which NLP technologies can help improve an award-winning tool developed by MS so that users are able to better understand and implement their legal rights freely.

Downscaling of Numerical Weather Prediction Data

Sept, 2021 - Dec, 2021

This was the MSc project of Shenbin Qian with the UK Met Office at the University of Exeter. The main purpose was to use low-resolution numerical weather prediction data to generate high-resolution data using deep learning techniques, especially single image super resolution (SR) techniques like SRCNN and SRGAN.

E-commerce Product Retrieval

Feb, 2023 - Dec, 2024

Led by Dr Diptesh Kanojia at University of Surrey, this project is funded by eBay to build lightweight contextual character-based embeddings for product retrieval. This research aims to improve search accuracy and relevance on eBay's e-commerce platforms.

Work Exeprience

Jul, 2024 - Present

Research Assistant in Natural Language Processing | University of Surrey

  • Develop efficient and effective language models for product retrieval on eBay's e-commerce platforms.

Jan, 2017 – Dec, 2020

Resource Engineer & Project Manager | Lancoo Group

  • Crawled English teaching resources online for human cleaning and annotation;
  • Established and maintained feature databases for knowledge recognition to identify English words, phrases and sentence (syntactic) patterns for teaching purposes, achieving an accuracy of 99%, 98% and 97% respectively;
  • Managed the whole team and the project, and cooperated with other teams to integrete the project into the AI-IOT Smart Campus Solution.

Nov, 2015 - Mar, 2017

Part-Time English Teacher | Hujiang English

  • Taught Chinese adult students basic spoken English and English pronunciation.

Apr, 2014 - Jun, 2014

Part-Time English Translator | Hithink Royalflush Information Network

  • Translated the profiles and financial information of listed companies.

Recent Awards

Jan, 2023

EAMT Award for Sponsorship of Student Activities

  • As part of its commitment to promote research, development and awareness about translation technologies, the European Association of Machine Translation (EAMT) for the third consecutive year launched a call for proposals to fund MT-related activities led by students during 2023.

Apr, 2022

Winner of the MSc Project Award

  • This was awarded to the student with the best project for the year on an Mathematics MSc Programmme in the University of Exeter.

Apr, 2020

Global Excellence Scholarship

  • The scholarship recipients were selected on academic merit and the ability to demonstrate academic ambition and future career ambitions.