Publications (11)
Prompt and circumstance: A word-by-word LLM prompting approach to interlinear glossing for low-resource languages
Micha Elsner, David Liu
Partly automated creation of interlinear glossed text (IGT) has the potential to assist in linguistic documentation. We argue that LLMs can make this process more accessible to lin…
Fairness-aware Summarization for Justified Decision-Making
Moniba Keymanesh, Tanya Berger-Wolf, Micha Elsner +1
In consequential domains such as recidivism prediction, facility inspection, and benefit assignment, it's important for individuals to know the decision-relevant information for th…
Exploring How Generative Adversarial Networks Learn Phonological Representations
Jingyi Chen, Micha Elsner
This paper explores how Generative Adversarial Networks (GANs) learn representations of phonological phenomena. We analyze how GANs encode contrastive and non-contrastive nasality…
Fine-Tuning Text-to-Speech Diffusion Models Using Reinforcement Learning with Human Feedback
Jingyi Chen, Ju Seung Byun, Micha Elsner +2
Diffusion models produce high-fidelity speech but are inefficient for real-time use due to long denoising steps and challenges in modeling intonation and rhythm. To improve this, w…
Shortcomings of LLMs for Low-Resource Translation: Retrieval and Understanding are Both the Problem
Sara Court, Micha Elsner
This work investigates the in-context learning abilities of pretrained large language models (LLMs) when instructed to translate text from a low-resource language into a high-resou…
Analogy in Contact: Modeling Maltese Plural Inflection
Sara Court, Andrea D. Sims, Micha Elsner
Maltese is often described as having a hybrid morphological system resulting from extensive contact between Semitic and Romance language varieties. Such a designation reflects an e…