{"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/binarized-neural-machine-translation-1","title":"Binarized Neural Machine Translation","arxiv_id":"2302.04907","date":"2023-02-09","proceeding":"NeurIPS 2023 11","authors":["Yichi Zhang","Ankush Garg","Yuan Cao","Łukasz Lew","Behrooz Ghorbani","Zhiru Zhang","Orhan Firat"],"abstract":"The rapid scaling of language models is motivating research using low-bitwidth quantization. In this work, we propose a novel binarization technique for Transformers applied to machine translation (BMT), the first of its kind. We identify and address the problem of inflated dot-product variance when using one-bit weights and activations. Specifically, BMT leverages additional LayerNorms and residual connections to improve binarization quality. Experiments on the WMT dataset show that a one-bit weight-only Transformer can achieve the same quality as a float one, while being 16x smaller in size. One-bit activations incur varying degrees of quality drop, but mitigated by the proposed architectural changes. We further conduct a scaling law study using production-scale translation datasets, which shows that one-bit weight Transformers scale and generalize well in both in-domain and out-of-domain settings. Implementation in JAX/Flax will be open sourced.","url_abs":"https://arxiv.org/abs/2302.04907v1","url_pdf":"https://arxiv.org/pdf/2302.04907v1.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":"binarized-neural-machine-translation-1","repo_url":"https://github.com/google/aqt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"binarization","task_name":"Binarization"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"quantization","task_name":"Quantization"},{"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":{"syntology_url":"https://syntology.ai/paper/2302.04907","atlas_url":"https://app.syntology.ai/?focus=2302.04907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04907"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/google/aqt","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":2},"by_repo_kind":{"official":{"samples":6,"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":"2bfc14ec361a1b0c","entry":"get_max_frac_in_binary","repo":"google/aqt","repo_kind":"official","path":"aqt/common/emulated_floating_points.py","file_url":"https://github.com/google/aqt/blob/HEAD/aqt/common/emulated_floating_points.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2bfc14ec361a1b0c"}},{"code_sha256_prefix":"d9571aead8ca0c4c","entry":"is_fp8_format","repo":"google/aqt","repo_kind":"official","path":"aqt/common/emulation_utils.py","file_url":"https://github.com/google/aqt/blob/HEAD/aqt/common/emulation_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9571aead8ca0c4c"}},{"code_sha256_prefix":"c20d67bdc6bc52a4","entry":"matmul","repo":"google/aqt","repo_kind":"official","path":"aqt/jax/aqt_matmul.py","file_url":"https://github.com/google/aqt/blob/HEAD/aqt/jax/aqt_matmul.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c20d67bdc6bc52a4"}},{"code_sha256_prefix":"eef63aa8933e4e4f","entry":"pass_through","repo":"google/aqt","repo_kind":"official","path":"aqt/jax/aqt_tensor.py","file_url":"https://github.com/google/aqt/blob/HEAD/aqt/jax/aqt_tensor.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eef63aa8933e4e4f"}},{"code_sha256_prefix":"ee238f6213016698","entry":"get_metadata","repo":"google/aqt","repo_kind":"official","path":"aqt/common/emulation_utils.py","file_url":"https://github.com/google/aqt/blob/HEAD/aqt/common/emulation_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ee238f6213016698"}},{"code_sha256_prefix":"2bacb2e16475ec99","entry":"is_e8_format","repo":"google/aqt","repo_kind":"official","path":"aqt/common/emulation_utils.py","file_url":"https://github.com/google/aqt/blob/HEAD/aqt/common/emulation_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2bacb2e16475ec99"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}