{"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/evidence-aggregation-for-answer-re-ranking-in","title":"Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering","arxiv_id":"1711.05116","date":"2017-11-14","proceeding":"ICLR 2018 1","authors":["Shuohang Wang","Mo Yu","Jing Jiang","Wei zhang","Xiaoxiao Guo","Shiyu Chang","Zhiguo Wang","Tim Klinger","Gerald Tesauro","Murray Campbell"],"abstract":"A popular recent approach to answering open-domain questions is to first\nsearch for question-related passages and then apply reading comprehension\nmodels to extract answers. Existing methods usually extract answers from single\npassages independently. But some questions require a combination of evidence\nfrom across different sources to answer correctly. In this paper, we propose\ntwo models which make use of multiple passages to generate their answers. Both\nuse an answer-reranking approach which reorders the answer candidates generated\nby an existing state-of-the-art QA model. We propose two methods, namely,\nstrength-based re-ranking and coverage-based re-ranking, to make use of the\naggregated evidence from different passages to better determine the answer. Our\nmodels have achieved state-of-the-art results on three public open-domain QA\ndatasets: Quasar-T, SearchQA and the open-domain version of TriviaQA, with\nabout 8 percentage points of improvement over the former two datasets.","url_abs":"http://arxiv.org/abs/1711.05116v2","url_pdf":"http://arxiv.org/pdf/1711.05116v2.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":"evidence-aggregation-for-answer-re-ranking-in","repo_url":"https://github.com/shuohangwang/mprc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"re-ranking","task_name":"Re-Ranking"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"reranking","task_name":"Reranking"},{"task_slug":"triviaqa","task_name":"TriviaQA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-domain-question-answering-on-quasar","task":"Open-Domain Question Answering","dataset":"Quasar","model":"Evidence Aggregation via R^3 Re-Ranking","rank_in_archive_order":1,"of":6,"metrics":{"EM (Quasar-T)":"42.3","F1 (Quasar-T)":"49.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1711.05116","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.05116"}},"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/shuohangwang/mprc","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran_violates":2,"ran_honours":2,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"147e0ae162d88334","entry":"add_triple_data","repo":"shuohangwang/mprc","repo_kind":"official","path":"trainedmodel/evaluation/unftriviaqa/utils/convert_to_squad_format.py","file_url":"https://github.com/shuohangwang/mprc/blob/HEAD/trainedmodel/evaluation/unftriviaqa/utils/convert_to_squad_format.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"147e0ae162d88334"}},{"code_sha256_prefix":"f6c275d6a18330a9","entry":"exact_match_score","repo":"shuohangwang/mprc","repo_kind":"official","path":"trainedmodel/evaluation/quasart/evaluate-v1.1.py","file_url":"https://github.com/shuohangwang/mprc/blob/HEAD/trainedmodel/evaluation/quasart/evaluate-v1.1.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f6c275d6a18330a9"}},{"code_sha256_prefix":"2c66ac5f9374f1f7","entry":"exact_match_score","repo":"shuohangwang/mprc","repo_kind":"official","path":"trainedmodel/evaluation/unftriviaqa/triviaqa_evaluation.py","file_url":"https://github.com/shuohangwang/mprc/blob/HEAD/trainedmodel/evaluation/unftriviaqa/triviaqa_evaluation.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2c66ac5f9374f1f7"}},{"code_sha256_prefix":"2112c433b9c6d343","entry":"f1_score","repo":"shuohangwang/mprc","repo_kind":"official","path":"trainedmodel/evaluation/quasart/evaluate-v1.1.py","file_url":"https://github.com/shuohangwang/mprc/blob/HEAD/trainedmodel/evaluation/quasart/evaluate-v1.1.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2112c433b9c6d343"}},{"code_sha256_prefix":"5d0a37a7c59decf8","entry":"f1_score","repo":"shuohangwang/mprc","repo_kind":"official","path":"trainedmodel/evaluation/unftriviaqa/triviaqa_evaluation.py","file_url":"https://github.com/shuohangwang/mprc/blob/HEAD/trainedmodel/evaluation/unftriviaqa/triviaqa_evaluation.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d0a37a7c59decf8"}},{"code_sha256_prefix":"c6a80c065d2e4851","entry":"normalize_answer","repo":"shuohangwang/mprc","repo_kind":"official","path":"trainedmodel/evaluation/quasart/evaluate-v1.1.py","file_url":"https://github.com/shuohangwang/mprc/blob/HEAD/trainedmodel/evaluation/quasart/evaluate-v1.1.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c6a80c065d2e4851"}},{"code_sha256_prefix":"2879260bc19381c8","entry":"normalize_answer","repo":"shuohangwang/mprc","repo_kind":"official","path":"trainedmodel/evaluation/unftriviaqa/triviaqa_evaluation.py","file_url":"https://github.com/shuohangwang/mprc/blob/HEAD/trainedmodel/evaluation/unftriviaqa/triviaqa_evaluation.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2879260bc19381c8"}},{"code_sha256_prefix":"b009e6d552a30ed2","entry":"select_relevant_portion","repo":"shuohangwang/mprc","repo_kind":"official","path":"trainedmodel/evaluation/unftriviaqa/utils/convert_to_squad_format.py","file_url":"https://github.com/shuohangwang/mprc/blob/HEAD/trainedmodel/evaluation/unftriviaqa/utils/convert_to_squad_format.py","link_basis":"first_harvest_node","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":"b009e6d552a30ed2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}