Peer-reviewed papers, manuscripts and talks on biomedical language resources, Vietnamese speech, medical machine translation, corpus linguistics and e-learning. * marks equal contribution.
English–Vietnamese parallel biomedical NER corpus with UMLS semantic types and cross-lingual benchmarks. Co-first author (* equal contribution).
34-hour dataset and benchmark for Vietnamese medical code-switched speech recognition: 16,576 utterances across five medical topics.
Phonetically informed data augmentation for robust Vietnamese speech translation.
Contrastive training with LLM-generated near-misses for robust code-switching ASR.
Introduces MedEV (~360K medical sentence pairs); fine-tuned models beat Google Translate. Co-first author (* equal contribution). Pages 8955–8962.
Corpus-based study of text-type variation in Vietnamese. Pages 221–225.
Authorship identification using stylometric measures of Vietnamese texts. Pages 447–452.
Corpus construction to support teaching Vietnamese as a foreign language. Pages 13–22.
Challenges in designing pedagogical scripts for e-learning. Pages 947–960.
Sampling criteria for building a representative Vietnamese corpus. Pages 26–32.
Corpus construction to support Vietnamese dictionary compilation. Pages 423–433.
First author. Describes the ViLEC learner corpus: 258 documents, 267,512 words, 15,129 sentences from five courses.
Built on the EV Shift Corpus, co-led by Nhu Vo. A human-validated LLM framework classifies 36,046 Vietnamese comments by evaluative orientation and five implementation concerns, showing how appraisal of Ho Chi Minh City's electric two-wheeler plan shifted around the July 2025 announcement.
Built on ViACS, a corpus co-led by Nhu Vo. Corpus-assisted critical discourse analysis of 179,391 news articles and 53,798 Facebook and YouTube comments (2017–2025), combining keyword statistics, sentiment analysis and concordance close reading.
Presents the group's Vietnamese–English medical speech translation application for communication between clinicians and patients.
Seminar on designing and building spoken-language corpora.
Corpus construction to support teaching Vietnamese as a foreign language.
Corpus-based comparison of part-of-speech distributions across two Vietnamese genres.
Analysis of collocations extracted automatically from a Vietnamese corpus.
Using a Vietnamese corpus for stylometric analysis and authorship study.
Design of the VVC Vietnamese corpus and its metadata annotation scheme.
