mlsanityData to 7 Oct 2026

Back to School: Translation Using Grammar Books

arXiv 2410.15263 ↗First posted 20 Oct 2024cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

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 quantity of parallel sentences needed to train such systems. These under-represented languages are not without resources, however, and bilingual dictionaries and grammar books are available as linguistic reference material. With current large language models (LLMs) supporting near book-length contexts, we can begin to use the available material to ensure advancements are shared among all of the world's languages. In this paper, we demonstrate incorporating grammar books in the prompt of GPT-4 to improve machine translation and evaluate the performance on 16 topologically diverse low-resource languages, using a combination of reference material to show that the machine translation performance of LLMs can be improved using this method.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 7 of its 15 references that are in the map. First posted on arXiv 20 Oct 2024.

Builds on

7 of 15 references.

References · 7

  1. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  2. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  3. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
  4. 2021Systematic Inequalities in Language Technology Performance across the World's Languagescited by 118
  5. 2023A Benchmark for Learning to Translate a New Language from One Grammar Bookcited by 74
  6. 2022Building Machine Translation Systems for the Next Thousand Languagescited by 69
  7. 2024Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptionscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 7.

11 papers.

  1. 2025Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchucited by 12
  2. 2025Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Bookscited by 4
  3. 2025The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlangcited by 3
  4. 2026Evaluating Extremely Low-Resource Machine Translation: A Comparative Study of ChrF++ and BLEU Metricscited by 2
  5. 2026Speaking of Language: Reflections on Metalanguage Research in NLPcited by 1
  6. 2025Testing the Limits of Machine Translation from One Bookcited by 0
  7. 2026Rashid: A Cipher-Based Framework for Exploring In-Context Language Learningcited by 0
  8. 2026Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusioncited by 0
  9. 2026Reinforcement Learning Elicits Contextual Learning of Unseen Language Translationcited by 0
  10. 2026A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar Bookscited by 0
  11. 2026LLM Agents as Computational Typologistscited by 0