GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ramos, Rita, Chimoto, Everlyn Asiko, ter Hoeve, Maartje, Schluter, Natalie
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915316319125504
author Ramos, Rita
Chimoto, Everlyn Asiko
ter Hoeve, Maartje
Schluter, Natalie
author_facet Ramos, Rita
Chimoto, Everlyn Asiko
ter Hoeve, Maartje
Schluter, Natalie
contents We introduce GrammaMT, a grammatically-aware prompting approach for machine translation that uses Interlinear Glossed Text (IGT), a common form of linguistic description providing morphological and lexical annotations for source sentences. GrammaMT proposes three prompting strategies: gloss-shot, chain-gloss and model-gloss. All are training-free, requiring only a few examples that involve minimal effort to collect, and making them well-suited for low-resource setups. Experiments show that GrammaMT enhances translation performance on open-source instruction-tuned LLMs for various low- to high-resource languages across three benchmarks: (1) the largest IGT corpus, (2) the challenging 2023 SIGMORPHON Shared Task data over endangered languages, and (3) even in an out-of-domain setting with FLORES. Moreover, ablation studies reveal that leveraging gloss resources could substantially boost MT performance (by over 17 BLEU points) if LLMs accurately generate or access input sentence glosses.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18702
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning
Ramos, Rita
Chimoto, Everlyn Asiko
ter Hoeve, Maartje
Schluter, Natalie
Computation and Language
We introduce GrammaMT, a grammatically-aware prompting approach for machine translation that uses Interlinear Glossed Text (IGT), a common form of linguistic description providing morphological and lexical annotations for source sentences. GrammaMT proposes three prompting strategies: gloss-shot, chain-gloss and model-gloss. All are training-free, requiring only a few examples that involve minimal effort to collect, and making them well-suited for low-resource setups. Experiments show that GrammaMT enhances translation performance on open-source instruction-tuned LLMs for various low- to high-resource languages across three benchmarks: (1) the largest IGT corpus, (2) the challenging 2023 SIGMORPHON Shared Task data over endangered languages, and (3) even in an out-of-domain setting with FLORES. Moreover, ablation studies reveal that leveraging gloss resources could substantially boost MT performance (by over 17 BLEU points) if LLMs accurately generate or access input sentence glosses.
title GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning
topic Computation and Language
url https://arxiv.org/abs/2410.18702