Papers › Modeling Voting for System Combination in Machine Translation

Modeling Voting for System Combination in Machine Translation

14 Jul 2020arXiv:2007.06943archive 2025-07-28

Xuancheng Huang, Jiacheng Zhang, Zhixing Tan, Derek F. Wong, Huanbo Luan, Jingfang Xu, Maosong Sun, Yang Liu

System combination is an important technique for combining the hypotheses of different machine translation systems to improve translation performance. Although early statistical approaches to system combination have been proven effective in analyzing the consensus between hypotheses, they suffer from the error propagation problem due to the use of pipelines. While this problem has been alleviated by end-to-end training of multi-source sequence-to-sequence models recently, these neural models do not explicitly analyze the relations between hypotheses and fail to capture their agreement because the attention to a word in a hypothesis is calculated independently, ignoring the fact that the word might occur in multiple hypotheses. In this work, we propose an approach to modeling voting for system combination in machine translation. The basic idea is to enable words in hypotheses from different systems to vote on words that are representative and should get involved in the generation process. This can be done by quantifying the influence of each voter and its preference for each candidate. Our approach combines the advantages of statistical and neural methods since it can not only analyze the relations between hypotheses but also allow for end-to-end training. Experiments show that our approach is capable of better taking advantage of the consensus between hypotheses and achieves significant improvements over state-of-the-art baselines on Chinese-English and English-German machine translation tasks.

PaperPDFCodeCode 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

The archive's official repository (THUNLP-MT/Voting4SC) was not harvested; the 19 samples below come from 1 repository the archive does not mark official.

Syntology 19 code samples harvested from 1 repository linked to this paper: 9 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; 9 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 19 samples from 1 repository, 9 ran (0 with no instrument failure; 9 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.

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.

THUNLP-MT/Voting4SC officialmentioned in papertfSyntology: not harvested 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.

Code Syntology ran Syntology

19 samples harvested: 9 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; 9 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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.

8ran · our draft was wrong
1ran; the contract check could not run
10unverified

Licence: 0 of the 19 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 THUNLP-MT/THUMT. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

THUNLP-MT/THUMT found in paper text by Syntology 19 samples, 9 ran (9 instrument-failed) · 10 unverified
_gather_2d thumt/utils/inference.py ran; the contract check could not run (RAISES) BSD-3-Clause (permissive) · f031547076b6075c · report fixture: signature params:Tensor/2/float, indices:Tensor/2/int, name:NoneType/0/? · returned Tensor · level recorded 2026-09-22
_get_inference_fn thumt/utils/inference.py ran · our draft was wrong BSD-3-Clause (permissive) · 463b3c15e786dbfe · report fixture: signature model_fns:list/1/callable, features:dict/0/? · returned function · level recorded 2026-09-24
_merge_first_two_dims thumt/utils/inference.py ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 3b4b7a09ba0ee2e6 · report fixture: signature tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-22
_sequence_like thumt/utils/inference.py ran · our draft was wrong BSD-3-Clause (permissive) · 561d5f639961744a · report fixture: signature instance:dict/0/?, args:list/1/int · returned dict · level recorded 2026-09-24
_sorted thumt/utils/inference.py ran · our draft was wrong BSD-3-Clause (permissive) · 5074d78b4ac1ef24 · report fixture: signature dict_:dict/0/? · returned list · level recorded 2026-09-22
_split_first_two_dims thumt/utils/inference.py ran · our draft was wrong BSD-3-Clause (permissive) · 9f94edc124e9bd63 · report fixture: signature tensor:Tensor/2/float, dim_0:int/0/int, dim_1:int/0/int · returned Tensor · level recorded 2026-09-22
_tile_to_beam_size thumt/utils/inference.py ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · cb65bec95376bc21 · report fixture: signature tensor:Tensor/2/float, beam_size:int/0/int · returned Tensor · level recorded 2026-09-22
_yield_flat_nest thumt/utils/inference.py ran · our draft was wrong BSD-3-Clause (permissive) · 985919b4b2337dc2 · report fixture: signature nest:dict/0/? · returned generator · level recorded 2026-09-22
_yield_value thumt/utils/inference.py ran · our draft was wrong BSD-3-Clause (permissive) · b8e5c1ce284001c0 · report fixture: signature iterable:dict/0/? · returned generator · level recorded 2026-09-22
BeamSearchState thumt/utils/inference.py unverified BSD-3-Clause (permissive) · 038543c35e853013 · report
_beam_search_step thumt/utils/inference.py unverified BSD-3-Clause (permissive) · 6554c0535ec778f7 · report
_packed_nest_with_indices thumt/utils/inference.py unverified BSD-3-Clause (permissive) · 89854118fa650f7c · report
_recursive_assert_same_structure thumt/utils/inference.py unverified BSD-3-Clause (permissive) · a743ab7b23275a39 · report
assert_same_structure thumt/utils/inference.py unverified BSD-3-Clause (permissive) · 3eb93923026ab511 · report
beam_search in 25 papers thumt/utils/inference.py unverified BSD-3-Clause (permissive) · 5ca040d32880306a · report
is_sequence in 10 papers thumt/utils/inference.py unverified BSD-3-Clause (permissive) · e98986abba883c3b · report
map_structure thumt/utils/inference.py unverified BSD-3-Clause (permissive) · de427ed06cf972f2 · report
pack_sequence_as thumt/utils/inference.py unverified BSD-3-Clause (permissive) · 596ed65af5de1fac · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for voting for system combination (graph method: voting for system combination). 19 bricks; individually on a fixture: 9 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; 9 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. beam_search entry · level 0 · unverified · 5ca040d32880306a
  2. BeamSearchState helper · level 0 · unverified · 038543c35e853013
  3. _beam_search_step helper · level 0 · unverified · 6554c0535ec778f7
  4. _get_inference_fn helper · level 1 · ran · our draft was wrong · 463b3c15e786dbfe
  5. _tile_to_beam_size helper · level 1 · ran · our draft was wrong · cb65bec95376bc21
  6. map_structure helper · level 0 · unverified · de427ed06cf972f2
  7. _gather_2d helper · level 1 · ran; the contract check could not run (RAISES) · f031547076b6075c
  8. _merge_first_two_dims helper · level 1 · ran · our draft was wrong · 3b4b7a09ba0ee2e6
  9. _split_first_two_dims helper · level 1 · ran · our draft was wrong · 9f94edc124e9bd63
  10. assert_same_structure helper · level 0 · unverified · 3eb93923026ab511
  11. flatten helper · level 0 · unverified · 8144ac299d399dfe
  12. pack_sequence_as helper · level 0 · unverified · 596ed65af5de1fac
  13. _recursive_assert_same_structure helper · level 0 · unverified · a743ab7b23275a39
  14. is_sequence helper · level 0 · unverified · e98986abba883c3b
  15. _yield_flat_nest helper · level 1 · ran · our draft was wrong · 985919b4b2337dc2
  16. _packed_nest_with_indices helper · level 0 · unverified · 89854118fa650f7c
  17. _sequence_like helper · level 1 · ran · our draft was wrong · 561d5f639961744a
  18. _yield_value helper · level 1 · ran · our draft was wrong · b8e5c1ce284001c0
  19. _sorted helper · level 1 · ran · our draft was wrong · 5074d78b4ac1ef24

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="2007.06943") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Machine TranslationTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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