Research

Research at NLP2CT Lab

From Portuguese–Chinese machine translation to large language models, evaluation and trustworthy AI.

Research Areas

01

Machine Translation

Neural and LLM-based translation for low-resource and multilingual settings, document-level and discourse-aware translation, Portuguese–Chinese translation, and the evaluation and quality estimation of translation systems.

02

Large Language Models

Training, alignment and instruction tuning of LLMs, data selection, reasoning from experience, uncertainty and self-evaluation, and benchmarks that measure what models really know.

03

Trustworthy and Safe AI

Detection of LLM-generated text, model safety under adversarial prompting, bias and debiasing, hallucination mitigation, and explainable and controllable generation.

04

Multimodal and Multilingual Understanding

Multimodal machine translation, vision-language models and their evaluation, speech and affective computing, and representation learning across languages.

05

LLM Agents and Applications

Agents for mathematics and science, medical and clinical NLP, personalised education, poetry translation and generation, and other interdisciplinary uses of language technology.

06

Language Resources and Tools

Large parallel corpora such as UM-Corpus and UM-pCorpus, the UM-CAT computer-aided translation platform, UM-NMT, dictionaries, morphological analysers and annotation toolkits.

Funded Projects 25

Supported by the National Natural Science Foundation of China (NSFC), the Science and Technology Development Fund of Macau (FDCT), the University of Macau Multi-Year Research Grant (MYRG) and industry partners.

ProjectFundingPeriodRole
Research and Development of Large Language Models for Intelligent Service Platforms in Information SecurityFDCT, Macao Funding Scheme for Key R&D Projects2025–2027Co-PI
Research on Chinese-Oriented Low-Resource Machine Translation TechnologiesNSFC-FDCT, FDCT/060/2022/AFJ2023–2025PI
Modularized Semantic Neural Machine Translation: Fundamentals & ApplicationMOST-FDCT, FDCT/070/2022/AMJ2022–2025PI
Pretraining-based Automatic Evaluation of Machine TranslationMYRG, MYRG-GRG2023-00006-FST-UMDF2024–2025PI
Large Language Models for Machine Translation with Enhanced Discourse ModelingTencent AI Lab Rhino-Bird Research Program2023–2024PI
Research of Non-Autoregressive Neural Machine TranslationMYRG, MYRG2020-00054-FST2021–2023PI
Guiding Self-Attention Based Neural Machine Translation with Linguistic Prior KnowledgeFDCT, 0101/2019/A22019–2022PI
Research of Chinese-Portuguese Machine Translation Based on Deep LearningNSFC-FDCT, FDCT/045/2017/AFJ2018–2020Co-PI
Research on Domain Adaptation for Low-Resource Chinese-Portuguese Machine Translation in Big Data Era: Methodology and Its ImplementationNSFC, 617022032017–2020PI
Morpho-Syntactic Modeling for Chinese-Portuguese Statistical Machine TranslationMYRG, MYRG2017-00087-FST2018–2020PI
Research on Linguistic Prediction Model with Graph-based Semi-Supervised LearningMYRG, MYRG2015-00188-FST2015–2018PI
Heterogeneous Domain Adaptation Model for SMTFDCT, 057/2014/A2015–2017PI
Domain Adaptation in Statistical Machine Translation Based on Graph PropagationMYRG, MYRG2015-00175-FST2015–2018PI
Model-Driven Software Development from Requirement Description to Code GenerationFDCT, 103/2015/A32016–2019Co-PI
AuTema-ReOrgS – Automatic Reorganization of StructuresMYRG, MYRG2016-00109-FAH2017–2019Co-PI
Construction of Portuguese-Chinese Parallel Treebank (PCTreeBank) Based on Unsupervised Learning ApproachMYRG, MYRG076(Y1-L2)-FST13-WF2013–2016PI
Computational Psycholinguistic Models of Second Language Processing and ProductionMYRG, MYRG064(Y1-L2)-FSH13-CCM2013–2016Co-PI
Blind Biosignal Classification (B2SC) Framework for a Multi-Function Health Alert DeviceMYRG, MYRG070(Y1-L2)-FST12-CS2012–2015Co-PI
AuTema-Post-Editing (AuTema-PostEd)MYRG, MYRG058(Y1-L2)-FSH12-ALL2012–2015Co-PI
Autema – SynTree – Annotation and Analysis of Bilingual Syntactic Trees for Chinese/PortugueseMYRG, MYRG102(Y1-L2)-FSH11-ALL2011–2014Co-PI
Syntax Modeling & Parsing for Portuguese-Chinese Machine Translation and Establishment of Macau Key Research Laboratory in NLP & MTFDCT, 057/2009/A22010–2013PI
Grammatical Inference for Analyzing the Second Language Acquisition of Spoken PortugueseMYRG, RG060/09-10S/11R/CS/FST2010–2012Co-PI
Data Mining Model in Analyzing the Acquisition of Portuguese Knowledge for Macau StudentsMYRG, RG054/08-09S/CS/FST2009–2010Co-PI
AuTema-Dis IIMYRG, RG035/09-10S/ALL/FSH2010–2011Co-PI
R&D of Knowledge-based Machine-Aided Bi-Directional Paragraph Translation in Portuguese-Chinese and English-ChineseFDCT, 041/2005/A2006–2009PI

Software & Data

UM-CAT

The University of Macau's online computer-aided translation platform for Portuguese, Chinese and English.

UM-NMT

Online neural machine translation for Portuguese and Chinese.

UM-Corpus

A large multi-domain English–Chinese parallel corpus for statistical machine translation (Tian et al., LREC 2014).

UM-pCorpus

A large Portuguese–Chinese parallel corpus (Chao et al., LREC 2018).

PCT-Dict / UM-Dict

The Portuguese–Chinese bidirectional electronic dictionary with more than 100,000 entries and trilingual pronunciation.

PCT-Assist

A machine-aided translation system for Portuguese and Chinese embedded in Microsoft Word, now superseded by UM-CAT.

SyntaxTree Builder & Aligner

An online parallel treebank annotation and construction platform with syntactic tree creation and parallel tree alignment (Xing et al., 2016).

Pomotion

Portuguese morphological variation analyser with a lemmatiser and verb conjugator.

Enmotion

English morphological variation analyser with a lemmatiser, inflector and verb conjugator.

iSentenizer-μ

A multilingual sentence boundary detection model based on the i+Learning incremental learning algorithm (Wong et al., 2014).

Open-source code

Implementations of the lab's papers, including Meta-Curriculum, Norm-Based Curriculum Learning, Uncertainty-Aware Curriculum Learning and Self-Paced Learning for NMT.

Awards & Recognition

  • 2025

    Best Paper Award, First Workshop on VLM4RWD at NeurIPS 2025 (VisAidMath).

  • 2024

    University-level Teaching Excellence Award 2023/2024 and FST Teaching Excellence Award, University of Macau (Prof. Derek F. Wong).

  • 2023

    Ranked 1st in Discourse-Level Literary Translation, Conference on Machine Translation (WMT 2023).

  • 2023

    Yu Sheng: Human-in-Loop Classical Chinese Poetry Generation System — First Prize, 17th Pan-Pearl River Delta+ University IT Project Competition; Third Prize, 10th 'Sharing Cup' Innovation Competition.

  • 2023

    Excellence Award, Tencent AI Lab Rhino-Bird Research Program.

  • 2022

    Second Prize, Technological Invention Award, Macao Science and Technology Awards 2022 — Linguistics-Driven Neural Machine Translation Model and Its Application in Chinese-Portuguese Machine Translation.

  • 2022

    Ranked 1st (multilingual and English–Russian) and 2nd (English–German and Chinese–English) in Quality Estimation, WMT 2022.

  • 2021

    Ranked 1st in Evaluation Metrics for Chinese/Czech/German/Japanese–English, and 2nd for Hausa/Icelandic–English, WMT 2021 (with Alibaba DAMO Academy).

  • 2017

    Ranked 1st and 2nd for Chinese–English newswire translation, 13th China Workshop on Machine Translation (CWMT 2017).

  • 2012

    Second-Class Prize, Science and Technology Progress Award, 1st Macao Science and Technology Awards — Technologies and Applications of Portuguese-Chinese Machine Translation System.