{"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/directed-acyclic-transformer-for-non","title":"Directed Acyclic Transformer for Non-Autoregressive Machine Translation","arxiv_id":"2205.07459","date":"2022-05-16","proceeding":null,"authors":["Fei Huang","Hao Zhou","Yang Liu","Hang Li","Minlie Huang"],"abstract":"Non-autoregressive Transformers (NATs) significantly reduce the decoding latency by generating all tokens in parallel. However, such independent predictions prevent NATs from capturing the dependencies between the tokens for generating multiple possible translations. In this paper, we propose Directed Acyclic Transfomer (DA-Transformer), which represents the hidden states in a Directed Acyclic Graph (DAG), where each path of the DAG corresponds to a specific translation. The whole DAG simultaneously captures multiple translations and facilitates fast predictions in a non-autoregressive fashion. Experiments on the raw training data of WMT benchmark show that DA-Transformer substantially outperforms previous NATs by about 3 BLEU on average, which is the first NAT model that achieves competitive results with autoregressive Transformers without relying on knowledge distillation.","url_abs":"https://arxiv.org/abs/2205.07459v1","url_pdf":"https://arxiv.org/pdf/2205.07459v1.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":"directed-acyclic-transformer-for-non","repo_url":"https://github.com/thu-coai/da-transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.07459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.07459"}},"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/thu-coai/da-transformer","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"ran_fixture":1,"ran_violates":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"c16270c5c7c1f2e7","entry":"logsumexp","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"c16270c5c7c1f2e7"}},{"code_sha256_prefix":"616f44af4c97547c","entry":"distinct","repo":"thu-coai/da-transformer","repo_kind":"official","path":"examples/DA-Transformer/evaluation/evaluate_personachat.py","file_url":"https://github.com/thu-coai/da-transformer/blob/HEAD/examples/DA-Transformer/evaluation/evaluate_personachat.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"616f44af4c97547c"}},{"code_sha256_prefix":"a2c97567e486a5af","entry":"inference_post_process","repo":"thu-coai/da-transformer","repo_kind":"official","path":"fs_plugins/models/glat_decomposed_with_link.py","file_url":"https://github.com/thu-coai/da-transformer/blob/HEAD/fs_plugins/models/glat_decomposed_with_link.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a2c97567e486a5af"}},{"code_sha256_prefix":"d302c4c00a9e7166","entry":"subprocess_init","repo":"thu-coai/da-transformer","repo_kind":"official","path":"fs_plugins/models/glat_decomposed_with_link.py","file_url":"https://github.com/thu-coai/da-transformer/blob/HEAD/fs_plugins/models/glat_decomposed_with_link.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d302c4c00a9e7166"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}