CLFeb 28, 2024

Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions

CMU
arXiv:2402.18025v221 citationsh-index: 60Has CodeACL
Originality Highly original
AI Analysis

This addresses the challenge of preserving and processing endangered languages for linguists and communities, though it is incremental as it builds on existing LLMs with a novel prompting method.

The paper tackles the problem of enabling large language models (LLMs) to process and translate endangered languages, which lack large training corpora, by proposing LINGOLLM, a training-free approach that uses linguistic descriptions in prompts. The result shows that LINGOLLM elevates translation capability from GPT-4's 0 to 10.5 BLEU for 10 language directions.

How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform well in unseen, endangered languages. On the contrary, we observe that 2000 endangered languages, though without a large corpus, have a grammar book or a dictionary. We propose LINGOLLM, a training-free approach to enable an LLM to process unseen languages that hardly occur in its pre-training. Our key insight is to demonstrate linguistic knowledge of an unseen language in an LLM's prompt, including a dictionary, a grammar book, and morphologically analyzed input text. We implement LINGOLLM on top of two models, GPT-4 and Mixtral, and evaluate their performance on 5 tasks across 8 endangered or low-resource languages. Our results show that LINGOLLM elevates translation capability from GPT-4's 0 to 10.5 BLEU for 10 language directions. Our findings demonstrate the tremendous value of linguistic knowledge in the age of LLMs for endangered languages. Our data, code, and model generations can be found at https://github.com/LLiLab/llm4endangeredlang.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes