{"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/non-monotonic-latent-alignments-for-ctc-based","title":"Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation","arxiv_id":"2210.03953","date":"2022-10-08","proceeding":null,"authors":["Chenze Shao","Yang Feng"],"abstract":"Non-autoregressive translation (NAT) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word positions. Latent alignment models relax the explicit alignment by marginalizing out all monotonic latent alignments with the CTC loss. However, they cannot handle non-monotonic alignments, which is non-negligible as there is typically global word reordering in machine translation. In this work, we explore non-monotonic latent alignments for NAT. We extend the alignment space to non-monotonic alignments to allow for the global word reordering and further consider all alignments that overlap with the target sentence. We non-monotonically match the alignments to the target sentence and train the latent alignment model to maximize the F1 score of non-monotonic matching. Extensive experiments on major WMT benchmarks show that our method substantially improves the translation performance of CTC-based models. Our best model achieves 30.06 BLEU on WMT14 En-De with only one-iteration decoding, closing the gap between non-autoregressive and autoregressive models.","url_abs":"https://arxiv.org/abs/2210.03953v1","url_pdf":"https://arxiv.org/pdf/2210.03953v1.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":"non-monotonic-latent-alignments-for-ctc-based","repo_url":"https://github.com/ictnlp/nmla-nat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"non-monotonic-latent-alignments-for-ctc-based","repo_url":"https://github.com/ictnlp/nast-s2x","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.03953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03953"}},"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/ictnlp/nmla-nat","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ictnlp/nast-s2x","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"8966a106dd26788e","entry":"ensemble_decoder","repo":"ictnlp/nmla-nat","repo_kind":"official","path":"fairseq/models/nat/fairseq_nat_model.py","file_url":"https://github.com/ictnlp/nmla-nat/blob/HEAD/fairseq/models/nat/fairseq_nat_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"8966a106dd26788e"}},{"code_sha256_prefix":"eaa91eaae9eb59f0","entry":"ensemble_encoder","repo":"ictnlp/nmla-nat","repo_kind":"official","path":"fairseq/models/nat/fairseq_nat_model.py","file_url":"https://github.com/ictnlp/nmla-nat/blob/HEAD/fairseq/models/nat/fairseq_nat_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"eaa91eaae9eb59f0"}},{"code_sha256_prefix":"a2543dc608ad4f8a","entry":"gumbel_noise","repo":"ictnlp/nmla-nat","repo_kind":"official","path":"fairseq/models/nat/iterative_nonautoregressive_transformer.py","file_url":"https://github.com/ictnlp/nmla-nat/blob/HEAD/fairseq/models/nat/iterative_nonautoregressive_transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a2543dc608ad4f8a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}