Background

The ongoing digital transformation and growing demands for accessibility have catalyzed a surge in translation and interpreting (T&I) services. These services now span multiple languages (multilingual), utilize various communication channels combining text, visuals, and audio (multimodal), and involve a range of agents, including humans, machines, and their hybrid forms (multiagent). In response to these complexities, Dr Han Chao have developed a robust and programmatic research agenda, termed Quality Assessment in Multilingual, Multimodal, and Multiagent Translation and Interpreting (QAM3T&I). The QAM3T&I framework addresses key aspects – agency, instrumentation, process, product, and reception – of T&I quality assessment (see Han, 2025). Its goal is to advance both manual and automatic evaluation methods across languages, communication channels, and agent types.

 

Beyond this primary research focus, Dr Han has also contributed to the field through meta-research, employing systematic reviews and meta-analyses to examine the methodological evolution and empirical trends in Translation Studies.

 

Current research projects

Dr. Han is currently engaged in several interrelated strands of research aimed at advancing the theory, methodology, and practice of evaluation and reception in translation and interpreting (T&I). His work draws on interdisciplinary approaches from applied linguistics, psychometrics, cognitive science, and natural language processing, and contributes to both human-centered and AI-driven assessment paradigms. His current research focuses on the following areas:

 

• a) Modeling the cognitive processes of human evaluators involved in assessing both human- and machine-generated T&I outputs, using process tracing methodologies such as eye-tracking, keystroke logging, and think-aloud protocols. This strand aims to uncover the mental operations and decision-making strategies evaluators engage in when judging T&I quality.

 

• b) Investigating the reception and processing of T&I products by human readers and listeners — across both human- and AI-generated outputs — through computational (psycholinguistic) approaches and multimodal behavioral data. This line of research seeks to understand how different types of T&I influence comprehension, cognitive load, trust, and communicative effectiveness.

 

• c) Applying, configuring, and fine-tuning large language models (LLMs) for automated T&I quality evaluation, with a particular focus on model reliability, alignment with human judgment, and internal and external validity. This includes the development and validation of LLM-based e-raters that can support or complement human evaluation in high-stakes assessment contexts.

 

• d) Exploring human–AI collaboration in the quantitative and qualitative evaluation of language performance, including T&I. This includes examining how human expertise and machine intelligence can be synergistically integrated in formative feedback, summative evaluation, and instructional contexts.

 

• e) Conducting meta-research through systematic reviews, bibliometric analyses, and meta-analyses to trace the evolution, trends, and methodological trajectories of T&I studies and language assessment, thereby informing future research directions and promoting evidence-based scholarship in the field.

 

PhD supervision

Dr. Han welcomes highly motivated PhD students from diverse academic backgrounds — including T&I studies, language assessment, computational linguistics, cognitive psychology, and related fields — to join his research group.

 

Prospective students interested in pursuing doctoral research under his supervision are encouraged to contact him via email (chaohan@nus.edu.sg) with a full research proposal, CV, and academic transcripts.