A Comparison of Fine-Tuning and In-Context Learning for Clause-Level Morphosyntactic Alternation
Jim Su, Justin Ho, George Aaron Broadwell, Sarah Moeller, Bonnie Jean Dorr · 2024
This paper presents our submission to the AmericasNLP 2024 Shared Task on the Creation of Educational Materials for Indigenous Languages.We frame this task as one of morphological inflection generation, treating each sentence as a single word.We investigate and compare two distinct approaches: fine-tuning neural encoder-decoder models such as NLLB-200, and in-context learning with proprietary large language models (LLMs).Our findings demonstrate that for this task, no one approach is perfect.Anthropic's Claude 3 Opus, when supplied with grammatical description entries, achieves the highest performance on Bribri among the evaluated models.This outcome corroborates and extends previous research exploring the efficacy of in-context learning in lowresource settings.For Maya, fine-tuning NLLB-200-3.3B using StemCorrupt augmented data yielded the best performance.