{"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/language-informed-beam-search-decoding-for","title":"Language-Informed Beam Search Decoding for Multilingual Machine Translation","arxiv_id":"2408.05738","date":"2024-08-11","proceeding":null,"authors":["Yilin Yang","Stefan Lee","Prasad Tadepalli"],"abstract":"Beam search decoding is the de-facto method for decoding auto-regressive Neural Machine Translation (NMT) models, including multilingual NMT where the target language is specified as an input. However, decoding multilingual NMT models commonly produces ``off-target'' translations -- yielding translation outputs not in the intended language. In this paper, we first conduct an error analysis of off-target translations for a strong multilingual NMT model and identify how these decodings are produced during beam search. We then propose Language-informed Beam Search (LiBS), a general decoding algorithm incorporating an off-the-shelf Language Identification (LiD) model into beam search decoding to reduce off-target translations. LiBS is an inference-time procedure that is NMT-model agnostic and does not require any additional parallel data. Results show that our proposed LiBS algorithm on average improves +1.1 BLEU and +0.9 BLEU on WMT and OPUS datasets, and reduces off-target rates from 22.9\\% to 7.7\\% and 65.8\\% to 25.3\\% respectively.","url_abs":"https://arxiv.org/abs/2408.05738v1","url_pdf":"https://arxiv.org/pdf/2408.05738v1.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":"language-informed-beam-search-decoding-for","repo_url":"https://github.com/yilinyang7/fairseq_multi_fix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-identification","task_name":"Language Identification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.05738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05738"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yilinyang7/fairseq_multi_fix","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"6e48c23d5c9f5b18","entry":"dot_product","repo":"yilinyang7/fairseq_multi_fix","repo_kind":"official","path":"fairseq/tasks/translation_multi_tgp.py","file_url":"https://github.com/yilinyang7/fairseq_multi_fix/blob/HEAD/fairseq/tasks/translation_multi_tgp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e48c23d5c9f5b18"}},{"code_sha256_prefix":"6c5c1eb7caad8f86","entry":"get_time_gap","repo":"yilinyang7/fairseq_multi_fix","repo_kind":"official","path":"fairseq/tasks/translation_multi_simple_epoch.py","file_url":"https://github.com/yilinyang7/fairseq_multi_fix/blob/HEAD/fairseq/tasks/translation_multi_simple_epoch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c5c1eb7caad8f86"}},{"code_sha256_prefix":"6a9226e4a161ee51","entry":"l2_norm","repo":"yilinyang7/fairseq_multi_fix","repo_kind":"official","path":"fairseq/tasks/translation_multi_tgp.py","file_url":"https://github.com/yilinyang7/fairseq_multi_fix/blob/HEAD/fairseq/tasks/translation_multi_tgp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a9226e4a161ee51"}},{"code_sha256_prefix":"9704f3c4359614ac","entry":"pcgrad_proj","repo":"yilinyang7/fairseq_multi_fix","repo_kind":"official","path":"fairseq/tasks/translation_multi_tgp.py","file_url":"https://github.com/yilinyang7/fairseq_multi_fix/blob/HEAD/fairseq/tasks/translation_multi_tgp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9704f3c4359614ac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}