{"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/modeling-voting-for-system-combination-in","title":"Modeling Voting for System Combination in Machine Translation","arxiv_id":"2007.06943","date":"2020-07-14","proceeding":null,"authors":["Xuancheng Huang","Jiacheng Zhang","Zhixing Tan","Derek F. Wong","Huanbo Luan","Jingfang Xu","Maosong Sun","Yang Liu"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2007.06943v1","url_pdf":"https://arxiv.org/pdf/2007.06943v1.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":"modeling-voting-for-system-combination-in","repo_url":"https://github.com/THUNLP-MT/Voting4SC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"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=2007.06943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06943"}},"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":"deterministic:regex_extraction","url":"https://github.com/THUNLP-MT/THUMT","reach":null}],"summary":{"ran_fixture":1,"ran":2,"ran_draft_wrong":6,"unverified":10},"by_repo_kind":{"found_in_text":{"samples":19,"ran":9,"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":"f031547076b6075c","entry":"_gather_2d","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f031547076b6075c"}},{"code_sha256_prefix":"463b3c15e786dbfe","entry":"_get_inference_fn","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"463b3c15e786dbfe"}},{"code_sha256_prefix":"3b4b7a09ba0ee2e6","entry":"_merge_first_two_dims","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3b4b7a09ba0ee2e6"}},{"code_sha256_prefix":"561d5f639961744a","entry":"_sequence_like","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"561d5f639961744a"}},{"code_sha256_prefix":"5074d78b4ac1ef24","entry":"_sorted","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5074d78b4ac1ef24"}},{"code_sha256_prefix":"9f94edc124e9bd63","entry":"_split_first_two_dims","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9f94edc124e9bd63"}},{"code_sha256_prefix":"cb65bec95376bc21","entry":"_tile_to_beam_size","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cb65bec95376bc21"}},{"code_sha256_prefix":"985919b4b2337dc2","entry":"_yield_flat_nest","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"985919b4b2337dc2"}},{"code_sha256_prefix":"b8e5c1ce284001c0","entry":"_yield_value","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b8e5c1ce284001c0"}},{"code_sha256_prefix":"038543c35e853013","entry":"BeamSearchState","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"038543c35e853013"}},{"code_sha256_prefix":"6554c0535ec778f7","entry":"_beam_search_step","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6554c0535ec778f7"}},{"code_sha256_prefix":"89854118fa650f7c","entry":"_packed_nest_with_indices","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"89854118fa650f7c"}},{"code_sha256_prefix":"a743ab7b23275a39","entry":"_recursive_assert_same_structure","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a743ab7b23275a39"}},{"code_sha256_prefix":"3eb93923026ab511","entry":"assert_same_structure","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3eb93923026ab511"}},{"code_sha256_prefix":"5ca040d32880306a","entry":"beam_search","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"5ca040d32880306a"}},{"code_sha256_prefix":"8144ac299d399dfe","entry":"flatten","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8144ac299d399dfe"}},{"code_sha256_prefix":"e98986abba883c3b","entry":"is_sequence","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e98986abba883c3b"}},{"code_sha256_prefix":"de427ed06cf972f2","entry":"map_structure","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"de427ed06cf972f2"}},{"code_sha256_prefix":"596ed65af5de1fac","entry":"pack_sequence_as","repo":"THUNLP-MT/THUMT","repo_kind":"found_in_text","path":"thumt/utils/inference.py","file_url":"https://github.com/THUNLP-MT/THUMT/blob/HEAD/thumt/utils/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"596ed65af5de1fac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}