{"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-autoregressive-streaming-transformer-for","title":"Non-autoregressive Streaming Transformer for Simultaneous Translation","arxiv_id":"2310.14883","date":"2023-10-23","proceeding":null,"authors":["Zhengrui Ma","Shaolei Zhang","Shoutao Guo","Chenze Shao","Min Zhang","Yang Feng"],"abstract":"Simultaneous machine translation (SiMT) models are trained to strike a balance between latency and translation quality. However, training these models to achieve high quality while maintaining low latency often leads to a tendency for aggressive anticipation. We argue that such issue stems from the autoregressive architecture upon which most existing SiMT models are built. To address those issues, we propose non-autoregressive streaming Transformer (NAST) which comprises a unidirectional encoder and a non-autoregressive decoder with intra-chunk parallelism. We enable NAST to generate the blank token or repetitive tokens to adjust its READ/WRITE strategy flexibly, and train it to maximize the non-monotonic latent alignment with an alignment-based latency loss. Experiments on various SiMT benchmarks demonstrate that NAST outperforms previous strong autoregressive SiMT baselines.","url_abs":"https://arxiv.org/abs/2310.14883v1","url_pdf":"https://arxiv.org/pdf/2310.14883v1.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-autoregressive-streaming-transformer-for","repo_url":"https://github.com/ictnlp/nast","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"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":"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=2310.14883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14883"}},"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/nast","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ictnlp/NAST","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran_honours":1,"ran":3},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"3c9757a9030277c7","entry":"ctc_decode","repo":"ictnlp/NAST","repo_kind":"official","path":"NAST/models/torch_imputer/imputer.py","file_url":"https://github.com/ictnlp/NAST/blob/HEAD/NAST/models/torch_imputer/imputer.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c9757a9030277c7"}},{"code_sha256_prefix":"e527b150dcb1fcaf","entry":"get_alignment_path","repo":"ictnlp/NAST","repo_kind":"official","path":"NAST/models/torch_imputer/imputer.py","file_url":"https://github.com/ictnlp/NAST/blob/HEAD/NAST/models/torch_imputer/imputer.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e527b150dcb1fcaf"}},{"code_sha256_prefix":"575ebd3590b18e59","entry":"get_anneal_value","repo":"ictnlp/NAST","repo_kind":"official","path":"NAST/criterions/utilities.py","file_url":"https://github.com/ictnlp/NAST/blob/HEAD/NAST/criterions/utilities.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"575ebd3590b18e59"}},{"code_sha256_prefix":"da87751db50ed191","entry":"merge_two_probs","repo":"ictnlp/NAST","repo_kind":"official","path":"NAST/generators/prefix_beam_search_logits.py","file_url":"https://github.com/ictnlp/NAST/blob/HEAD/NAST/generators/prefix_beam_search_logits.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"da87751db50ed191"}},{"code_sha256_prefix":"bcfc4f30d3191b80","entry":"parse_anneal_argument","repo":"ictnlp/NAST","repo_kind":"official","path":"NAST/criterions/utilities.py","file_url":"https://github.com/ictnlp/NAST/blob/HEAD/NAST/criterions/utilities.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bcfc4f30d3191b80"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}