paper-with-me

홈 › Papers

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

2024-10-24 · Rita Ramos, Everlyn Asiko Chimoto, Maartje ter Hoeve, Natalie Schluter

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.

📄 PDF Abstract BibTeX arXiv:2410.18702

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context LearningMachine TranslationSentenceTranslation

Similar Papers 제목 키워드 기반

Multi-Target Machine Translation with Multi-Synchronous Context-free Grammars

2015-05-01 · HLT 2015 5 · Kevin Duh, Graham Neubig, Philip Arthur
Language ModelingLanguage ModellingMachine TranslationSentence+1

Back to School: Translation Using Grammar Books

2024-10-20 · Jonathan Hus, Antonios Anastasopoulos

Machine translation systems for high resource languages perform exceptionally well and produce high quality translations. Unfortunately, the vast majority of languages are not considered high resource and lack the quanti…

Machine TranslationTranslation

Learning synchronous context-free grammars with multiple specialised non-terminals for hierarchical phrase-based translation

2020-04-03 · Felipe Sánchez-Martínez, Juan Antonio Pérez-Ortiz, Rafael C. Carrasco

Translation models based on hierarchical phrase-based statistical machine translation (HSMT) have shown better performances than the non-hierarchical phrase-based counterparts for some language pairs. The standard approa…

ClusteringMachine TranslationTranslation

Non-autoregressive Machine Translation with Probabilistic Context-free Grammar

2023-11-14 · NeurIPS 2023 11 · Shangtong Gui, Chenze Shao, Zhengrui Ma, Xishan Zhang 외

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to aut…

Machine TranslationTranslation

Bayesian Synchronous Grammar Induction

2008-12-01 · NeurIPS 2008 12 · Phil Blunsom, Trevor Cohn, Miles Osborne

We present a novel method for inducing synchronous context free grammars (SCFGs) from a corpus of parallel string pairs. SCFGs can model equivalence between strings in terms of substitutions, insertions and deletions, an…

Machine TranslationTranslation