Nguyen Anh Tu

Ha Dong, Ha Noi, Vietnam

H +84-964******

B advpoi@r.postjobfree.com

Í My Webpage

Github Linkedin Skype

Education

2016–2021: Bachelor Engineer Degree, Posts and Telecommunications Institute of Technology, Hanoi, Vietnam.

Major:Information Technology

Programing, Data structures and algorithms, Analysis & design of information systems Thesis (9.2/10): Information extraction from legal questions Research Experience

Posts and Telecommunications Institute of Technology, Hanoi, Vietnam 2019-present Legal Text Processing, Research and develop neural network architecture to extract information from legal text and spoken language processing.

Supervisor : Dr Ngo Xuan Bach, Associate Professor, Vice Dean of Faculty of Information Technology,Posts and Telecommunications Institute of Technology (PTIT), Hanoi, Vietnam. (Personal Web-page) Job Experience

10/2020-

1/2021

Technology Specialist, Vingroup Big Data Institute.

{ Vietnamese Text Sentiment Classification

- Developed classification models based on feature engineering and deep learning.

- Classification model reach top 1 private testset of AIVIVN challenging.

{ Vietnamese Accent Restorer

- Developed accent recovering models based on sequence labeling and sequence to sequence models. 2/2021-

3/2022

Applied Scientist, Vinbrain JSC.

{ Automatic Radiology Report Editing Through Voice

- Developed the NLP controller model based on JointBERT model for detecting intent and extracting content command of doctor

- Deployed NLP controller and integrate with ASR service

{ Medical equipment registration classification system for ministry of health

- Developed machine reading comprehension model based on XLM-R model to extract information from document (support both English and Vietnamese)

- Optimized machine reading comprehension model using knowledge distillation, quantization and transform pre-trained multi language model to bi language model

- Integrated OCR model, NLP model to classify the power of attorney

{ Automatic speech recognition system

- Developed a joint learning model to recover capitalization and punctuation

- Developed a spoken norm model to transform spoken language to written language 4/2022-

present

Research Engineer, Samsung SDS R&D Center, Vietnam.

{ Vietnamese Question Answering System

- Developed Machine Reading Comprehension model reach top 1 on private testset of VLSP 2021 challenging

- Optimized model architecture and runtime for MRC model using knowledge distillation and quantiza- tion

{ Vietnamese Korean machine translation

- Built large scale high quality Vietnamese-Korean machine translation dataset

- Developed machine translation model based on mBART Computer skills

Programming

Languages

Python, JAVA, C/C++

Frameworks

and libraries

Pytorch, Scikit-learn, Numpy, Pandas, Matplotlib, Flask, Huggingface, TensorRT, Triton server, ONNX, FastAPI

Software

Develop-

ment

Programming Pradigms, GIT, Docker, Linux

Languages Vietnamese: Native, English: IELTS 6.5

Honors and Awards

{ Bronze Medal, Google AI4Code – Understand Code in Python Notebooks, Kaggle Competitions

{ Consolation prize in ACM/ICPC PTIT 2019 programming contest

{ The first prize in Machine translation challenge hosted by VLSP2022 Publications

Journal Articles

2022 Oanh Thi Tran, Thang Van Nguyen, Tu Anh Nguyen, and Ngo Xuan Bach. Learning student intents and named entities in the education domain. International Journal on Artificial Intelligence Tools. accepted, SCIE Q3, 2022, ( Impact Factor:1.208 ). In Conference Proceedings

2023 Nguyen Anh Tu, Duong Xuan Hieu, Tu Minh Phuong, and Ngo Xuan Bach. A bidirectional joint model for spoken language understanding. In under review ICASSP, 2023. 2022 Hoang Thi Thu Uyen, Nguyen Anh Tu, and Ta Duc Huy. Vietnamese capitalization and punctuation recovery models. In Interspeech, 2022. 2022 Tran Ngoc Son*, Nguyen Anh Tu*, and Nguyen Minh Tri. An efficient approach for machine translation on low-resource languages: A case study in vietnamese-chinese. In Proceedings of the 9th International Workshop on Vietnamese Language and Speech Processing (to appear), 2022. 2021 Nguyen Anh Tu, Hoang Thi Thu Uyen, Tu Minh Phuong, and Ngo Xuan Bach. Analyzing vietnamese legal questions using deep neural networks with biaffine classifiers. In International Conference on Neural Information Processing, pages 513–525. Springer, 2021. 2021 Manh Hung Nguyen, Vu Hoang, Tu Anh Nguyen, and Trung H. Bui. Automatic Radiology Report Editing Through Voice. In Proc. Interspeech 2021, pages 4862–4863, 2021. 2021 Ta Duc Huy, Nguyen Anh Tu, Tran Hoang Vu, Nguyen Phuc Minh, Nguyen Phan, Trung H Bui, and Steven QH Truong. Vimq: A vietnamese medical question dataset for healthcare dialogue system development. In International Conference on Neural Information Processing, pages 657–664. Springer, 2021.

Contact this candidate