Nhu VoResearch Assistant · NLP & LLMs
Contact
Nhu Vo  /  CV

Curriculum vitae

NLP & LLM Researcher · Computer Science Educator · PhD Student, UTS & VinUniversity

Download CV (PDF)Last updated ·
Sydney (Ultimo), NSW, Australiavodiepnhu@gmail.comvodiepnhu.github.io LinkedIn Google Scholar VinUni Medical MT

Australian work rights: Student visa (subclass 500); no limit on working hours as a PhD student.

01

Profile

NLP researcher and university educator with seven years of language-data and NLP research and teaching appointments spanning 2017–2025. My PhD (UTS–VinUniversity) develops datasets, models and evaluation workflows for Vietnamese–English medical translation and biomedical information extraction: I led MedEV (about 360K medical sentence pairs) and co-led En-ViMedNER (202,949 aligned entities across 21 UMLS types). I have taught programming, computer science, NLP and information systems at eight institutions, including English-medium teaching at VinUniversity, and managed applied projects with clinicians, government departments and software partners. Open to research positions (Research Assistant/Associate, postdoctoral), lecturing roles and NLP/LLM roles in industry.

02

Core strengths

Research
Biomedical and low-resource NLP; NMT and LLM-based translation; cross-lingual NER; LLM evaluation and translation reliability; dataset and benchmark construction.
Engineering & data
Python, PyTorch, Hugging Face Transformers; fine-tuning, prompting and evaluation; corpus construction, Label Studio and LLM-assisted annotation; hands-on use of LangChain, LangGraph, Docker and AWS in prototypes.
Teaching
Programming, computer science, NLP and information systems; curriculum and syllabus design; blended and online delivery (Moodle, Canvas, Google Classroom, Articulate Storyline 360, SCORM); student research supervision.
Delivery
Project coordination with clinicians, government departments and software vendors; quality assurance; technical writing.
03

Education

PhD, Computer Science — Collaborative Research Degree

Apr 2023 – present

University of Technology Sydney & VinUniversity

NLP and LLMs for biomedical and low-resource machine translation.

  • Supervisors: Prof. Wray Buntine (Monash University); Asst Prof. Dung D. Le (VinUniversity); Prof. Massimo Piccardi and Dr Iñigo Jauregi Unanue (UTS).

Teaching qualification: Certificate of Pedagogical Training for College and University Lecturers, Saigon University (Dec 2020).

04

Research & professional experience

Research Assistant & Project Coordinator

Apr 2023 – present

VinUniversity, College of Engineering & Computer Science

Concurrent appointments within the UTS–VinUniversity collaborative PhD program; medical MT group with Prof. Wray Buntine and Asst Prof. Dung D. Le, in collaboration with UTS and VinUniversity College of Health Sciences.

  • Built MedEV (about 360K English–Vietnamese medical sentence pairs); fine-tuned and benchmarked Transformer translation models in both directions. Co-first-author paper, LREC-COLING 2024.
  • Co-led En-ViMedNER: 44,892 sentence pairs from 4,392 PubMed abstracts and 202,949 aligned entity mentions across 21 UMLS types. Translations were post-edited by doctors and medical students; LLM-projected entity spans were human-checked, reaching 98.32% entity exact match on a 450-sentence reviewed mini-test (κ = 0.83).
  • Co-developed ViMedCSS (34 hours; 16,576 utterances); contributed to two Interspeech 2026 papers on robust speech translation and code-switching ASR.
  • Coordinate the Robust Vietnamese–English Clinical and Educational Medical Translation project (Oct 2024 – present), including a real-time medical speech-translation prototype.

Project Manager, Smart Green Transformation Center (GREEN-X)

Apr 2022 – present

VinUniversity

  • Managed a web/mobile monitoring and evaluation platform with Bamboo Software; coordinated requirements and quality assurance with 10 Khanh Hoa provincial departments (Nov 2024 – Nov 2025).
  • Lead domain-specific Vietnamese corpora for computational social science: anti-corruption discourse (180K+ news texts, 50K+ social-media comments) and the electric-vehicle transition; managed a 1,622-talk business-speech corpus (12.5M+ words).

Remote AI Trainer — Vietnamese Writing

Apr 2024 – Sep 2025

Outlier · also Remote Vietnamese Transcriber, Appen (Feb 2022 – Sep 2025)

  • Wrote Vietnamese prompts and evaluated generative-AI responses against quality guidelines; transcribed and annotated Vietnamese audio for speech-data projects.

Open resources: En-ViMedNER, MedEV and ViMedCSS on Hugging Face; VnC 1.0, ViLEC and the Business Speeches Corpus (12.5M+ words) available on request.

05

Teaching experience

Visiting Faculty (CBM) & Teaching Assistant (CECS)

Apr 2023 – Sep 2025

VinUniversity, Hanoi · English-medium teaching

  • Visiting Faculty, College of Business and Management (Oct 2024 – Sep 2025): taught Management Information Systems and Spreadsheet Modelling for Business to undergraduates.
  • Teaching Assistant, College of Engineering & Computer Science (Apr 2023 – Sep 2025): tutorials and assessment for Natural Language Processing; Big Ideas: AI and the Knowledge Revolution; Research Communication; Health Informatics; Introduction to Programming with Python; Computational & Algorithmic Thinking.

Lecturer, Department of English Teaching Methodology

Apr 2021 – Feb 2022

Nguyen Tat Thanh University (NTTU), Faculty of Foreign Languages · English-medium teaching

  • Designed syllabi and learning resources for E-learning in English Language Teaching and Instructional Technology in English Language Teaching.
  • Guided 65 student research projects on online course design; supervised two undergraduate theses (2021, 2022) and Business English internships. Led ViLEC, a learner corpus of 258 student documents (267,512 words; 15,129 sentences).

Visiting Lecturer, Faculties of Information Technology

May 2020 – Apr 2023

Ho Chi Minh City University of Economics and Finance (UEF), 2021 – 2023 · University of Science, Vietnam National University Ho Chi Minh City (VNU-HCMUS), 2020 – 2021

  • UEF: taught Introductory Computer Science and coordinated online delivery through the university LMS.
  • VNU-HCMUS: practice lecturer for Introduction to NLP (High-Quality Program) and tutor for Computer Hardware (Advanced Program, in English); developed flipped-classroom syllabi for Statistical Linguistics and Text Mining and Applications.

Lecturer; Team Leader from Aug 2019

May 2017 – Feb 2020

Ho Chi Minh City University of Education (HCMUE), Information Technology Center

  • Taught Basic Informatics; developed online curricula, syllabi and e-learning scripts aligned with approved course outlines.
  • Led the university team building and rolling out VLE.HCMUE with ACP Singapore, funded by the World Bank and Vietnam's Ministry of Education and Training. Developed Moodle courses for 3,000+ high-school teachers; trainer in ETEP and the National Foreign Language 2020 Project.

Other teaching: Visiting Lecturer, Web Interface Design, Ly Tu Trong College and District 12 Technical-Economic College (2022). Head of Kits-based Department, SUMATO Academy (Jan – Jun 2020): Scratch, LEGO Mindstorms EV3 and Python curricula; trained teachers.

06

Publications

* Equal contribution. Full list: Google Scholar.

Peer-reviewed international conference papers

  1. Nhu Vo*, Phuong Nguyen*, Nu Uyen Phuong Le, Iñigo Jauregi Unanue, Dung D. Le, Massimo Piccardi, and Wray Buntine. 2026. En-ViMedNER: An English–Vietnamese parallel biomedical corpus with UMLS semantic type annotations. Findings of EMNLP 2026.
  2. Giang Son Nguyen, Tung X. Nguyen, Hieu Minh Truong, Nhu Vo, Wray Buntine, and Dung D. Le. 2026. PiDA: Phonetically-informed data augmentation for robust Vietnamese speech translation. Interspeech 2026.
  3. Tung X. Nguyen*, Hieu Minh Truong*, Giang Son Nguyen, Nhu Vo, Wray Buntine, and Dung D. Le. 2026. Contrastive training with LLM-generated near-misses for robust code-switching speech recognition. Interspeech 2026.
  4. Tung X. Nguyen, Nhu Vo, Giang-Son Nguyen, Duy Mai Hoang, Chien Dinh Huynh, Iñigo Jauregi Unanue, Massimo Piccardi, Wray Buntine, and Dung D. Le. 2026. ViMedCSS: A Vietnamese medical code-switching speech dataset & benchmark. LREC 2026.
  5. Nhu Vo*, Dat Quoc Nguyen*, Dung D. Le, Massimo Piccardi, and Wray Buntine. 2024. Improving Vietnamese–English medical machine translation. LREC-COLING 2024, 8955–8962.
  6. Nhu Vo, Thuy Bui, and Dien Dinh. 2020. Text-type variation in Vietnamese: Corpus mining for linguistic features in narrative and non-narrative genres. NICS 2020 (IEEE), 221–225.
  7. Lam Ho, Nhu Vo, Dien Dinh, and Nhung Nguyen. 2020. Identifying authors based on stylometric measures of Vietnamese texts. PACLIC 34, 447–452.

Journal articles

  1. Nhu Vo, Thuy Bui, Tran Phan, and Dien Dinh. 2022. Vietnamese corpus construction for teaching Vietnamese to foreigners. Linguistic Journal (Vietnam Institute of Linguistics), 375(1), 13–22.
  2. Long Le and Nhu Vo. 2019. Pedagogical script: Challenges to be resolved in e-learning. HCMC University of Education Journal of Science, 16(12), 947–960.

National conference proceedings (Vietnam)

  1. Nhu Vo and Dien Dinh. 2020. Language sampling criteria for Vietnamese corpus construction. FAIR 2020, 26–32.
  2. Nhu Vo and Dien Dinh. 2020. Building a Vietnamese corpus for dictionary compilation. Vietnamese Dictionary and Encyclopedia: Theory and Practice, 423–433.

Manuscripts

  • First author. ViLEC: Design, Annotation, and Pedagogical Applications of a Vietnamese Learner English Corpus. Under review, SAGE Open.
  • Co-author. Data-Driven Equity-Sensitive Urban Mobility Planning: LLM-Based Policy Appraisal of Ho Chi Minh City's Two-Wheeler Electrification. Under review, Journal of Urban Mobility.
  • Co-author. Anti-corruption discourse across news and social media in Vietnam (2017–2025): A corpus-assisted critical analysis. Under review, Critical Discourse Studies.
07

Research projects & funding

  • VinUniversityRobust Vietnamese–English Clinical and Educational Medical TranslationProject Coordinator2024 – present
  • VinUniversityDomain-specific Vietnamese Corpora: Anti-Corruption; EV ShiftCo-investigator2025 – present
  • VinUniversityGreen Transformation M&E System, Khanh HoaProject Manager2024 – 2025
  • VinUniversityBusiness Speeches CorpusCo-investigator2022 – 2023
  • EarlierViLEC, NTTULead2021 – 2022
  • EarlierVnC 1.0, VNU-HCMUSLead2020 – 2021
  • EarlierNLP Engine, HUFLIT2022 – 2023
08

Presentations

  • 2024SHARE 2024, Monash University: Vietnamese–English medical translation AI for healthcare communication (Buntine et al.)
  • 2022–2023Guest Speaker, Google Data Analytics (Module 8), NIC & Google
  • 2022Spoken corpus construction, FIT-HUFLIT Seminar Series
  • 2020Five co-authored talks, Linguistics and Application Areas Conference, VNU-HCMUSSH
09

Certifications, awards & languages

Awards

  • 2025Vingroup Science & Technology Scholarship for Overseas Doctoral Study
  • 2025UTS Collaborative Research Degree Scholarship
  • 2023VinUniversity Full PhD Scholarship
  • 2021VNU-HCM Postgraduate Scholarship
  • 2020ACP (Singapore) Certificate of Appreciation

Certifications

  • 2022DataCamp: Introduction to Python, Intermediate Python, Introduction to NLP in Python, Data Visualization with Matplotlib
  • IBMPython 101 for Data Science

Languages

Vietnamese (native); English (professional working proficiency).

10

Referees

Last updated · 10 November 2026Download PDF