Isaac Thompson

Education

Publications

1. 01

   AmanaMT: Translation Direction Predicts Automatic Metric Reliability

   Sole author

   Benchmarked 10 MT evaluation metrics across 730,748 segments and 33 languages. Translation direction is the strongest predictor of metric–human agreement (η² = 0.31), far ahead of morphological type (η² = 0.07). Also identifies a Simpson's Paradox in multi-year evaluation.

   WMT 2026 @ EMNLP
2. 02

   Bringing Mapudungun into the Modern MT Ecosystem

   First author

   Fine-tuned NLLB-200 on Mapudungun–Spanish across eight tokenization strategies. A novel Morfessor-VC segmentation matches a 5× larger model on arn→es (43.2 vs. 42.9 chrF++).

   AmericasNLP 2026 @ ACL

Working Papers

1. 01

   Drawing Legs on a Snake: Handling Out-of-Vocabulary Characters in Pretrained Chinese MT

   First author

   Found that pretrained MT models can't represent many Chinese characters, and showed that a new embedding per missing character fixes names and ordinary words while radical-based decomposition never helps; proposed a dictionary-plus-pronunciation initialization for characters with no training data.

   In preparation
2. 02

   Span F1 Misreads Cross-Lingual Retrieval

   First author

   Multilingual needle-in-a-haystack tests score correct English answers as wrong. This artifact explains most of the non-Latin-script gap. It also manufactures cross-script transfer from fine-tuning and reshuffles MLQA rankings across 33 models in lm-evaluation-harness. We propose script-aware scoring as a drop-in fix.

   In preparation
3. 03

   Lost in Translation or Lost in the Model?

   First author

   Do multilingual LLMs flatten culturally untranslatable words, like Portuguese saudade, toward their English glosses? A matched-pair study of 105 untranslatable concepts across 28 languages and 7 models finds they don't. Untranslatables stay consistently farther from English than exact translations through the models' middle layers, and this holds after removing language-identity effects.

   In preparation
4. 04

   Donor or Seed? Separating Donor Effects from Training Noise in Low-Resource Translation

   Co-author

   Shows that comparing donor languages for low-resource NLLB fine-tuning on single runs mostly measures seed noise. A donor × seed variance decomposition across six targets finds donor effects are real but small, and similarity proxies fail to predict them.

   In preparation
5. 05

   Speech Registers for Multimodal MT

   Co-author

   Applies source-token registration (Qu et al. 2025) to improve zero-shot performance across all four {S,T}×{S,T} MT directions; benchmarks NLLB-200 (3.3B), fine-tuned NLLB (600M), and Whisper across 420 directions and 8 language pairs.

   In preparation

Experience

Skills

Technical

Python (PyTorch, HuggingFace, PEFT/LoRA, Pandas, NumPy), SLURM / HPC cluster computing, Git, Bash / Linux, LaTeX, R, SQL, AWS (RDS, EC2), Claude Code

Languages

Native English, Fluent Spanish, Fluent Portuguese, Basic Mandarin Chinese

Interests

Low-Resource MT, Multimodal & Speech MT, Linguistically Informed NLP, LLM Fine-Tuning & Evaluation, Model Interpretability

Relevant Coursework

Upcoming

AI Harness Engineering (CS 401R), Readings in Machine Translation (CS 704R)

Graduate

Evaluation Metrics for Language Models (CS 501R), Transformers in NLP (CS 574), Advanced Machine Translation (CS 601R), AI Model Interpretability (CS 601R), Advanced Deep Learning (CS 674), Readings in Prosocial Language Models (CS 704R)

Undergraduate

Intro to Machine Learning (CS 270), Deep Learning (CS 474), Intro to Machine Translation (CS 479), full BS CS curriculum