Papers › Neural Machine Translation of Rare Words with Subword Units

Neural Machine Translation of Rare Words with Subword Units

31 Aug 2015ACL 2016 8arXiv:1508.07909archive 2025-07-28

Rico Sennrich, Barry Haddow, Alexandra Birch

Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem. Previous work addresses the translation of out-of-vocabulary words by backing off to a dictionary. In this paper, we introduce a simpler and more effective approach, making the NMT model capable of open-vocabulary translation by encoding rare and unknown words as sequences of subword units. This is based on the intuition that various word classes are translatable via smaller units than words, for instance names (via character copying or transliteration), compounds (via compositional translation), and cognates and loanwords (via phonological and morphological transformations). We discuss the suitability of different word segmentation techniques, including simple character n-gram models and a segmentation based on the byte pair encoding compression algorithm, and empirically show that subword models improve over a back-off dictionary baseline for the WMT 15 translation tasks English-German and English-Russian by 1.1 and 1.3 BLEU, respectively.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 30 code samples harvested from 7 repositories linked to this paper: 21 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 20 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 19 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 4 ran (0 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 24 samples from 6 repositories, 17 ran (1 with no instrument failure; 16 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 8 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

26 repositories listed; official and paper-mentioned ones first.

rsennrich/subword-nmt officialSyntology: 6 samples, 4 ran (4 instrument-failed) · 2 unverified report
Automattic/wp-translate mentioned on GitHubtfSyntology: not harvested report
Avmb/code-docstring-corpus mentioned on GitHubSyntology: not harvested report
EdinburghNLP/code-docstring-corpus mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A parallel corpus of Python functions and documentation strings for automated code... (arXiv:1707.02275; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
HarshKhandelwal1552/Language_classifier_with_Naive_Bayes mentioned on GitHubMITSyntology: not harvested report
SeonbeomKim/Python-Bype_Pair_Encoding mentioned on GitHubSyntology: not harvested report
SeonbeomKim/Python-Byte_Pair_Encoding mentioned on GitHubSyntology: 9 samples, 7 ran (7 instrument-failed) · 2 unverified report
ThAIKeras/bert mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Xinsen-Zhang/transformer mentioned on GitHubpaddleSyntology: not harvested report
facebookresearch/fairseq mentioned on GitHubpytorchMITSyntology: not harvested report
glample/fastBPE mentioned on GitHubMITSyntology: not harvested report
johnr0/TaleBrush-backend mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GeDi: Generative Discriminator Guided Sequence Generation (arXiv:2009.06367; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
karpathy/minbpe mentioned on GitHubSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
kh-mo/QA_wikisql mentioned on GitHubSyntology: 5 samples, 4 ran (4 instrument-failed) · 1 unverified report
ksulima/Unsupervised-method-to-NPL-Polish-language mentioned on GitHubSyntology: not harvested report
lkfo415579/MT-Readling-List mentioned on GitHubtfSyntology: not harvested report
nyu-dl/dl4mt-c2c mentioned on GitHubBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fully Character-Level Neural Machine Translation without Explicit Segmentation (arXiv:1610.03017; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
nyu-dl/dl4mt-cdec mentioned on GitHubBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation (arXiv:1603.06147; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
nyu-dl/dl4mt-simul-trans mentioned on GitHubSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
salesforce/GeDi mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GeDi: Generative Discriminator Guided Sequence Generation (arXiv:2009.06367; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
simonjisu/NMT mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Massive Exploration of Neural Machine Translation Architectures (arXiv:1703.03906; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
siyuofzhou/CNNSeqToSeq mentioned on GitHubtorchSyntology: not harvested report
thinkwee/DPP_CNN_Summarization mentioned on GitHubpytorchSyntology: 5 samples, 2 ran (2 instrument-failed) · 3 unverified report
VKCOM/YouTokenToMe MITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BPE-Dropout: Simple and Effective Subword Regularization (arXiv:1910.13267; that paper's own run record: 24 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 1 violated, 14 with no contract checked; 9 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
google/sentencepiece tfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Optimized Tokenization for Transcribed Error Correction (arXiv:2310.10704; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

30 samples harvested: 21 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 20 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

19ran · our draft was wrong
1ran; the contract check could not run
1ran
9unverified

Licence: 21 of the 30 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 7 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

rsennrich/subword-nmt official repository 6 samples, 4 ran (4 instrument-failed) · 2 unverified
get_pair_statistics subword_nmt/learn_bpe.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · fe96394f96a9c638 · report fixture: signature vocab:list/1/tuple · returned tuple · level recorded 2026-09-22
get_vocabulary in 11 papers subword_nmt/learn_bpe.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · b83d785ca99bfc9f · report fixture: signature fobj:TextIOWrapper/0/?, is_dict:bool/0/bool, is_bytes:bool/0/bool, num_workers:int/0/int · returned Counter · level recorded 2026-09-22
open_file in 10 papers subword_nmt/learn_bpe.py ran · our draft was wrong MIT (permissive) · 6aafe96a739d0b09 · report fixture: signature filename:str/0/str, mode:str/0/str · returned _GeneratorContextManager · level recorded 2026-09-22
replace_pair subword_nmt/learn_bpe.py ran · our draft was wrong MIT (permissive) · ab293eff6ffc4b69 · report fixture: signature pair:tuple/1/bytes, vocab:dict/0/?, indices:dict/0/?, is_bytes:bool/0/bool · returned list · level recorded 2026-09-24
_get_vocabulary subword_nmt/learn_bpe.py unverified MIT (permissive) · 800b6a080cb3c624 · report
learn_bpe subword_nmt/learn_bpe.py unverified MIT (permissive) · d86dc2151a1bd58e · report
SeonbeomKim/Python-Byte_Pair_Encoding community (archive-listed) 9 samples, 7 ran (7 instrument-failed) · 2 unverified
check_merge_info bpe_module/learn_BPE.py ran · our draft was wrong no licence file found · pointer only · 2032a0c86da75680 · report fixture: signature pairs:dict/0/? · returned str · level recorded 2026-09-22
delete_some_stats bpe_module/learn_BPE.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · c837ac919bdfe91e · report fixture: signature stats:dict/0/?, best_pair:tuple/1/int · returned dict · level recorded 2026-09-22
get_stats in 37 papers bpe_module/learn_BPE.py ran · our draft was wrong no licence file found · pointer only · afdbbe2995c004e2 · report fixture: signature word_frequency_list:list/1/tuple · returned dict · level recorded 2026-09-22
get_vocabulary_from_learn_BPE bpe_module/learn_BPE.py ran · our draft was wrong no licence file found · pointer only · afac3ba7a001359e · report fixture: signature word_frequency:list/1/tuple · returned list · level recorded 2026-09-22
merge_bpe_word bpe_module/learn_BPE.py ran · our draft was wrong no licence file found · pointer only · 029694838a73e5fc · report fixture: signature best_pair_and_word_frequency_list:list/1/tuple · returned list · level recorded 2026-09-22
merge_dictionary bpe_module/learn_BPE.py ran · our draft was wrong no licence file found · pointer only · 72ccea7ec0eb1e6a · report fixture: signature dic_a:dict/0/?, dic_b:dict/0/? · returned dict · level recorded 2026-09-22
selective_get_stats bpe_module/learn_BPE.py ran · our draft was wrong no licence file found · pointer only · c0d8d4efee4a4015 · report fixture: signature data:list/1/tuple · returned dict · level recorded 2026-09-22
_learn_bpe bpe_module/learn_BPE.py unverified no licence file found · pointer only · 133f6dc75e90bbd6 · report
save_voca bpe_module/learn_BPE.py unverified no licence file found · pointer only · e2122ad711c160ec · report
ThAIKeras/bert community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
BPE bpe_helper.py ran fingerprinted Apache-2.0 (permissive) · 33b1567b39f86e71 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
karpathy/minbpe community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
render_token minbpe/base.py ran · our draft was wrong MIT (permissive) · 1c202c7e568439b5 · report fixture: signature t:bytes/0/? · returned str · level recorded 2026-09-22
replace_control_characters minbpe/base.py ran · our draft was wrong fingerprinted MIT (permissive) · 15d9c32bbe7da76f · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
Tokenizer in 16 papers minbpe/base.py unverified MIT (permissive) · 293d3695d53b0cb1 · report
kh-mo/QA_wikisql community (archive-listed) 5 samples, 4 ran (4 instrument-failed) · 1 unverified
get_pair_statistics learn_bpe.py ran · our draft was wrong no licence file found · pointer only · e27a7ada9b96b37e · report fixture: signature file:list/1/tuple · returned tuple · level recorded 2026-09-22
get_vocabulary in 11 papers learn_bpe.py ran · our draft was wrong no licence file found · pointer only · 9425aef3e44f6979 · report fixture: signature file:StringIO/0/? · returned Counter · level recorded 2026-09-22
learn_bpe learn_bpe.py ran · our draft was wrong no licence file found · pointer only · a4985508aef2cb2a · report fixture: signature args:Args/0/? · returned list · level recorded 2026-09-22
replace_pair learn_bpe.py ran · our draft was wrong no licence file found · pointer only · d1027b3c5283677a · report fixture: signature pair:tuple/1/str, vocab:dict/0/?, indices:dict/0/? · returned list · level recorded 2026-09-22
update_pair_statistics learn_bpe.py unverified no licence file found · pointer only · c5fcb9cba4915130 · report
nyu-dl/dl4mt-simul-trans community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
_bpe2words simultrans_model.py ran · our draft was wrong BSD-3-Clause (permissive) · 70a8fed9225c5845 · report fixture: signature capsw:list/1/str · returned list · level recorded 2026-09-22
thinkwee/DPP_CNN_Summarization community (archive-listed) 5 samples, 2 ran (2 instrument-failed) · 3 unverified
get_vocabulary in 11 papers fairseq/raw_dataset/subword_nmt/learn_bpe.py ran · our draft was wrong no licence file found · pointer only · bc7574327ea1f634 · report fixture: signature fobj:StringIO/0/?, is_dict:bool/0/bool · returned Counter · level recorded 2026-09-22
replace_pair fairseq/raw_dataset/subword_nmt/learn_bpe.py ran · our draft was wrong no licence file found · pointer only · 684c47713cee0e44 · report fixture: signature pair:tuple/1/str, vocab:dict/0/?, indices:dict/0/? · returned list · level recorded 2026-09-22
learn_bpe fairseq/raw_dataset/subword_nmt/learn_bpe.py unverified no licence file found · pointer only · 0c8c96b6d6bd911a · report
prune_stats fairseq/raw_dataset/subword_nmt/learn_bpe.py unverified no licence file found · pointer only · 927c3c1d2631e415 · report
update_pair_statistics fairseq/raw_dataset/subword_nmt/learn_bpe.py unverified no licence file found · pointer only · 718aeb6813392ac3 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

7 assemblies on this paper: 7 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

7 sibling assemblies for subword units for open-vocabulary translation (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for subword units for open-vocabulary translation (graph method: subword units for open-vocabulary translation). 5 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. learn_bpe entry · level 1 · ran · our draft was wrong · a4985508aef2cb2a
  2. get_pair_statistics data_transform · level 1 · ran · our draft was wrong · e27a7ada9b96b37e
  3. get_vocabulary data_transform · level 1 · ran · our draft was wrong · 9425aef3e44f6979
  4. replace_pair helper · level 1 · ran · our draft was wrong · d1027b3c5283677a
  5. update_pair_statistics helper · level 0 · unverified · c5fcb9cba4915130

harvested Assembly for subword units for open-vocabulary translation (graph method: subword units for open-vocabulary translation). 9 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. _learn_bpe entry · level 0 · unverified · 133f6dc75e90bbd6
  2. check_merge_info helper · level 1 · ran · our draft was wrong · 2032a0c86da75680
  3. delete_some_stats helper · level 1 · ran; the contract check could not run (RAISES) · c837ac919bdfe91e
  4. get_stats helper · level 1 · ran · our draft was wrong · afdbbe2995c004e2
  5. get_vocabulary_from_learn_BPE helper · level 1 · ran · our draft was wrong · afac3ba7a001359e
  6. merge_bpe_word helper · level 1 · ran · our draft was wrong · 029694838a73e5fc
  7. merge_dictionary helper · level 1 · ran · our draft was wrong · 72ccea7ec0eb1e6a
  8. save_voca helper · level 0 · unverified · e2122ad711c160ec
  9. selective_get_stats helper · level 1 · ran · our draft was wrong · c0d8d4efee4a4015

harvested Assembly for subword units for open-vocabulary translation (graph method: subword units for open-vocabulary translation). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. _bpe2words entry · level 1 · ran · our draft was wrong · 70a8fed9225c5845

harvested Assembly for subword units for open-vocabulary translation (graph method: subword units for open-vocabulary translation). 6 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. learn_bpe entry · level 0 · unverified · 0c8c96b6d6bd911a
  2. get_pair_statistics helper · level 1 · ran · our draft was wrong · fe96394f96a9c638
  3. get_vocabulary data_transform · level 1 · ran · our draft was wrong · bc7574327ea1f634
  4. prune_stats helper · level 0 · unverified · 927c3c1d2631e415
  5. replace_pair helper · level 1 · ran · our draft was wrong · 684c47713cee0e44
  6. update_pair_statistics helper · level 0 · unverified · 718aeb6813392ac3

harvested Assembly for subword units for open-vocabulary translation (graph method: subword units for open-vocabulary translation). 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. Tokenizer entry · level 0 · unverified · 293d3695d53b0cb1
  2. render_token helper · level 1 · ran · our draft was wrong · 1c202c7e568439b5
  3. replace_control_characters helper · level 1 · ran · our draft was wrong · 15d9c32bbe7da76f

harvested Assembly for subword units for open-vocabulary translation (graph method: subword units for open-vocabulary translation). 8 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. learn_bpe entry · level 0 · unverified · d86dc2151a1bd58e
  2. get_pair_statistics helper · level 1 · ran · our draft was wrong · fe96394f96a9c638
  3. get_vocabulary helper · level 1 · ran · our draft was wrong · b83d785ca99bfc9f
  4. prune_stats helper · level 0 · unverified · 927c3c1d2631e415
  5. replace_pair helper · level 1 · ran · our draft was wrong · ab293eff6ffc4b69
  6. update_pair_statistics helper · level 0 · unverified · 718aeb6813392ac3
  7. _get_vocabulary helper · level 0 · unverified · 800b6a080cb3c624
  8. open_file helper · level 1 · ran · our draft was wrong · 6aafe96a739d0b09

harvested Assembly for subword units for open-vocabulary translation (graph method: subword units for open-vocabulary translation). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. BPE entry · level 1 · ran · 33b1567b39f86e71

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1508.07909") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Machine TranslationNMTSegmentationTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Machine Translation WMT2015 English-German BPE word segmentation BLEU score 22.8 #4 of 6 Archive leaderboard report
Machine Translation WMT2015 English-Russian C2-50k Segmentation BLEU score 20.9 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: BPE

BPE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections