{"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/dyrex-dynamic-query-representation-for","title":"DyREx: Dynamic Query Representation for Extractive Question Answering","arxiv_id":"2210.15048","date":"2022-10-26","proceeding":null,"authors":["Urchade Zaratiana","Niama El Khbir","Dennis Núñez","Pierre Holat","Nadi Tomeh","Thierry Charnois"],"abstract":"Extractive question answering (ExQA) is an essential task for Natural Language Processing. The dominant approach to ExQA is one that represents the input sequence tokens (question and passage) with a pre-trained transformer, then uses two learned query vectors to compute distributions over the start and end answer span positions. These query vectors lack the context of the inputs, which can be a bottleneck for the model performance. To address this problem, we propose \\textit{DyREx}, a generalization of the \\textit{vanilla} approach where we dynamically compute query vectors given the input, using an attention mechanism through transformer layers. Empirical observations demonstrate that our approach consistently improves the performance over the standard one. The code and accompanying files for running the experiments are available at \\url{https://github.com/urchade/DyReX}.","url_abs":"https://arxiv.org/abs/2210.15048v1","url_pdf":"https://arxiv.org/pdf/2210.15048v1.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":"dyrex-dynamic-query-representation-for","repo_url":"https://github.com/urchade/dyrex","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"extractive-question-answering","task_name":"Extractive Question-Answering"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-naturalqa","task":"Question Answering","dataset":"NaturalQA","model":"DyREX","rank_in_archive_order":4,"of":4,"metrics":{"F1":"78.58"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-newsqa","task":"Question Answering","dataset":"NewsQA","model":"DyREX","rank_in_archive_order":18,"of":18,"metrics":{"F1":"68.53"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"DyREX","rank_in_archive_order":212,"of":213,"metrics":{"F1":"91.01"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-triviaqa","task":"Question Answering","dataset":"TriviaQA","model":"DyREX","rank_in_archive_order":52,"of":56,"metrics":{"F1":"77.37"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.15048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15048"}},"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/urchade/DyReX","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/urchade/dyrex","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"9df40357afea56cc","entry":"to_list","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"9df40357afea56cc"}},{"code_sha256_prefix":"f2519ad21a2974bd","entry":"DyRExDecoder","repo":"urchade/dyrex","repo_kind":"official","path":"dyrex_qa.py","file_url":"https://github.com/urchade/dyrex/blob/HEAD/dyrex_qa.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f2519ad21a2974bd"}},{"code_sha256_prefix":"19b6e935db2624c7","entry":"DyRexQA","repo":"urchade/dyrex","repo_kind":"official","path":"dyrex_qa.py","file_url":"https://github.com/urchade/dyrex/blob/HEAD/dyrex_qa.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"19b6e935db2624c7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}