- UM-Corpus: A large, multi-domain English-Chinese parallel corpus (Tian et al., 2014).
- UM-pCorpus: A Large Portuguese-Chinese Parallel Corpus (Chao et al., 2018).
- Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning, ICLR 2021. [pdf] [code]
- Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation, AAAI 2021. [pdf] [code]
- Norm-Based Curriculum Learning for Neural Machine Translation, ACL 2020. [pdf] [code]
- Uncertainty-Aware Curriculum Learning for Neural Machine Translation, ACL 2020. [pdf] [code]
- Unsupervised Neural Dialect Translation with Commonality and Diversity Modeling, AAAI 2020. [pdf] [code]
- Self-Paced Learning for Neural Machine Translation, EMNLP 2020. [pdf] [code]
- Assessing the Ability of Self-Attention Networks to Learn Word Order, ACL 2019. [pdf] [code]
- Leveraging Local and Global Patterns for Self-Attention Networks, ACL 2019. [pdf] [code]
- UM-CAT: The University of Macau’s online computer-aided translation platform for Portuguese, Chinese, and English.
- UM-NMT: An online neural machine translation for Portuguese and Chinese.
- PCT-Dict/UM-Dict: The Portuguese-Chinese bidirectional electronic dictionary.
- PCT-Assist: A machine-aided translation system for Portuguese and Chinese. This stand-alone software has been replaced by the online UM-CAT system (Wong and Chao, 2010).
- TransLite: A language-independent translation framework based on Constraint Synchronous Grammar.
- SyntaxTree Builder & Aligner: An online parallel treebank annotation and construction platform, featured with syntactic creation and parallel tree alignment functions (Xing et al., 2016).
- Pomotion: Portuguese Morphological Variation analyzer, featured with word lemmatizer and verb conjugator.
- Enmotion: English Morphological Variation analyzer, featured with word lemmatizer, inflector, and verb conjugator.
- iSentenizer-μ: A multilingual Sentence Boundary Detection Model based on i+Learning (Intelligent and Incremental Learning) algorithm (Wong et al., 2014).