{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/back-to-school-translation-using-grammar","title":"Back to School: Translation Using Grammar Books","arxiv_id":"2410.15263","date":"2024-10-20","proceeding":null,"authors":["Jonathan Hus","Antonios Anastasopoulos"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2410.15263v1","url_pdf":"https://arxiv.org/pdf/2410.15263v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"back-to-school-translation-using-grammar","repo_url":"https://github.com/jonathanhus/back-to-school","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.15263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15263"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/jonathanhus/back-to-school","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"63195ea86c7b2b4f","entry":"count_grammar_book","repo":"jonathanhus/back-to-school","repo_kind":"official","path":"utilities/count_data.py","file_url":"https://github.com/jonathanhus/back-to-school/blob/HEAD/utilities/count_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63195ea86c7b2b4f"}},{"code_sha256_prefix":"bd1960932c46719e","entry":"count_sentences","repo":"jonathanhus/back-to-school","repo_kind":"official","path":"utilities/count_data.py","file_url":"https://github.com/jonathanhus/back-to-school/blob/HEAD/utilities/count_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd1960932c46719e"}},{"code_sha256_prefix":"bdd4c45f6daf0dab","entry":"count_words","repo":"jonathanhus/back-to-school","repo_kind":"official","path":"utilities/count_data.py","file_url":"https://github.com/jonathanhus/back-to-school/blob/HEAD/utilities/count_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdd4c45f6daf0dab"}},{"code_sha256_prefix":"b00b30f2d1ae0f3d","entry":"get_indices_dict","repo":"jonathanhus/back-to-school","repo_kind":"official","path":"utilities/get_common_sentences.py","file_url":"https://github.com/jonathanhus/back-to-school/blob/HEAD/utilities/get_common_sentences.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b00b30f2d1ae0f3d"}},{"code_sha256_prefix":"7d95d91a47fdb095","entry":"summarize_grammar","repo":"jonathanhus/back-to-school","repo_kind":"official","path":"utilities/format_grammar_book.py","file_url":"https://github.com/jonathanhus/back-to-school/blob/HEAD/utilities/format_grammar_book.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d95d91a47fdb095"}},{"code_sha256_prefix":"b12d2c2268d2c019","entry":"write_common_output","repo":"jonathanhus/back-to-school","repo_kind":"official","path":"utilities/get_common_sentences.py","file_url":"https://github.com/jonathanhus/back-to-school/blob/HEAD/utilities/get_common_sentences.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b12d2c2268d2c019"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}