Dung Nguyen Manh

I’m Dung (Dzung). I graduated with honors degree in Computer Science from University of Engineering and Technology, Vietnam National University (UET).

Since 2022, I’ve been working as a researcher and engineer at FPT Software AI Center’s AI Residency program, where I received guidance from Dr. Nghi Bui from Singapore Management University.

In my current role as an AI researcher, I’m all about embedding Machine Learning, Deep Learning into Software systems to solve problems like code search, code summarization, code generation, etc. The ultimate goal of my research is to revolutionize the way software is developed, improving its effectiveness, dependability, and accessibility. I aim to develop AI-powered tools that can seamlessly understand, produce, and optimize source code, minimizing human effort and error.

Therefore, I’m also working on AI-powered solutions for real-world software problems, like suggeting comments for source code and extracting code structures for AI models. Lately, with the wave of Large Language Models, I spent my work on integrating LLMs into coding-assist Chatbots and Unit-test generator for developer.

I’m best reached via email. I’m always up for dicussions, collaboration, or opportunities to pursue higher education abroad.

news

Oct 8, 2023	I happy to share that our work on The Vault has been accepted to EMNLP Findings 2023. See more details HERE.
Oct 5, 2022	I got my Bachelor degree in Computer Science from University of Engineering and Technology, Vietnam National Unviersity (CGPA: 3.61).
Jul 10, 2022	I was offered to become full-time AI Resident at FPTSoftware AI Center

selected publications

EMNLP’23
The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation

Dung Nguyen Manh, Nam Le Hai, Anh T. V. Dau, Anh Minh Nguyen, Khanh Nghiem, Jin Guo, and Nghi D. Q. Bui

2023

Abs arXiv Bib PDF Code

We present The Vault, an open-source, large-scale code-text dataset designed to enhance the training of code-focused large language models (LLMs). Existing open-source datasets for training code-based LLMs often face challenges in terms of size, quality (due to noisy signals), and format (only containing code function and text explanation pairings). The Vault overcomes these limitations by providing 40 million code-text pairs across 10 popular programming languages, thorough cleaning for 10+ prevalent issues, and various levels of code-text pairings, including class, function, and line levels. Researchers and practitioners can utilize The Vault for training diverse code-focused LLMs or incorporate the provided data cleaning methods and scripts to improve their datasets. By employing The Vault as the training dataset for code-centric LLMs, we anticipate significant advancements in code understanding and generation tasks, fostering progress in both artificial intelligence research and software development practices.
@misc{manh2023vault, title = {The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation}, author = {Manh, Dung Nguyen and Hai, Nam Le and Dau, Anh T. V. and Nguyen, Anh Minh and Nghiem, Khanh and Guo, Jin and Bui, Nghi D. Q.}, year = {2023}, eprint = {2305.06156}, archiveprefix = {arXiv}, primaryclass = {cs.CL}, }
ViWOZ: A Multi-Domain Task-Oriented Dialogue Systems Dataset For Low-resource Language

Phi Nguyen Van, Tung Cao Hoang, Dung Nguyen Manh, Quan Nguyen Minh, and Long Tran Quoc

2022

Abs arXiv Bib PDF

Most of the current task-oriented dialogue systems (ToD), despite having interesting results, are designed for a handful of languages like Chinese and English. Therefore, their performance in low-resource languages is still a significant problem due to the absence of a standard dataset and evaluation policy. To address this problem, we proposed ViWOZ, a fully-annotated Vietnamese task-oriented dialogue dataset. ViWOZ is the first multi-turn, multi-domain tasked oriented dataset in Vietnamese, a low-resource language. The dataset consists of a total of 5,000 dialogues, including 60,946 fully annotated utterances. Furthermore, we provide a comprehensive benchmark of both modular and end-to-end models in low-resource language scenarios. With those characteristics, the ViWOZ dataset enables future studies on creating a multilingual task-oriented dialogue system.
@misc{van2022viwoz, title = {ViWOZ: A Multi-Domain Task-Oriented Dialogue Systems Dataset For Low-resource Language}, author = {Van, Phi Nguyen and Hoang, Tung Cao and Manh, Dung Nguyen and Minh, Quan Nguyen and Quoc, Long Tran}, year = {2022}, eprint = {2203.07742}, archiveprefix = {arXiv}, primaryclass = {cs.CL}, }