Timothy Pistotti

Introductions

I am a PhD candidate at the University of Auckland, where my research focuses on Natural Language Processing (NLP) for low-resource languages. My work aims to develop methods that enable language technologies to function effectively for the vast number of languages that lack large-scale data resources.

My primary interests include cross-lingual transfer learning, computational syntax, and the intersection of linguistics and machine learning.

I recently built an interactive map showing the distribution of languages supported by several recent language models. Feel free to explore it below or open it in a full window.

---

Featured Publications

NoteBriGap-2 Workshop, Sept 2025 (Düsseldorf, Germany)

I recently presented two papers at the second workshop on Bridges and Gaps between Formal and Computational Linguistics:

1. Evaluating The Impact of Stimulus Quality in Investigations of {LLM} Language Performance
2. Exploring Gaps in the APS: Direct Minimal Pair Analysis in LLM Syntactic Assessments

Thanks to Jason Brown and Michael Witbrok, my Co-Authors on these papers.

NoteUncertaiNLP 2025, Nov 9 (Suzhou, China) - Presented Remotely

My presentation at the 2nd Workshop on Uncertainty-Aware NLP (co-located with EMNLP) highlighted how we can use model perplexity as a reliable indicator of naturalness in machine translations:

3. The Benefits of Being Uncertain: Perplexity as a Signal for Naturalness in Multilingual Machine Translation

Thanks to my Co-Authors: Michael Witbrock, Padriac Amato Tahua O’Leary, and Jason Brown.

For a complete list of my publications, please see my Google Scholar profile or the Publications page.