Hyewon Jang
Computational linguist
About Me
I received a PhD in computational linguistics at the University of Konstanz,
advised
by Diego Frassinelli
and
Bettina Braun.
My PhD project focused on analyzing how
language models process pragmatic information
that makes human language sophisticated and nuanced. I did it
by conducting psycholinguistic experiments and analyzing the collected data from multiple angles.
As a result, my PhD thesis is about
the examination of computational sarcasm detection through the
lens of psycholinguistics.
From August 2025, I will join CLASP at the University of Gothenburg as a postdoctoral researcher, where I will work on a project about the
role of multimodal context for sentence acceptability judgment, with Sharid Loáiciga,
Shalom Lappin, and Jey Han Lau.
Research Interests
- Psycholinguistic experiments: I test hypotheses about linguistic topics by conducting online experiments for human participants.
- Computational linguistics: I probe the capabilities of language models using the ideas and data from psycholinguistics. Comparing the behaviors of models and humans serves as a useful indicator for understanding what models can or can't do.
- Multimodality: Communication through language happens in multiple modalities. I examine the effects of textual and audiovisual modalities on human communication.
- Pragmatics and discouse: A lot of complexity occurs in human language, especially at the discourse level, and one of the reasons for that is the use of subtle pragmatics. I investigate the ways in which we can pull these complexities out of an utterance and make it clearer, so that language models can process pragmatic meaning better.
- Emotion and motivation: An utterance is often the result of underlying emotions and motivations. I use these underlying elements to analyze the capabilities of language models.