{"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/bridging-the-kb-text-gap-leveraging","title":"Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA","arxiv_id":"2308.14436","date":"2023-08-28","proceeding":null,"authors":["Guanting Dong","Rumei Li","Sirui Wang","Yupeng Zhang","Yunsen Xian","Weiran Xu"],"abstract":"Knowledge Base Question Answering (KBQA) aims to answer natural language questions with factual information such as entities and relations in KBs. However, traditional Pre-trained Language Models (PLMs) are directly pre-trained on large-scale natural language corpus, which poses challenges for them in understanding and representing complex subgraphs in structured KBs. To bridge the gap between texts and structured KBs, we propose a Structured Knowledge-aware Pre-training method (SKP). In the pre-training stage, we introduce two novel structured knowledge-aware tasks, guiding the model to effectively learn the implicit relationship and better representations of complex subgraphs. In downstream KBQA task, we further design an efficient linearization strategy and an interval attention mechanism, which assist the model to better encode complex subgraphs and shield the interference of irrelevant subgraphs during reasoning respectively. Detailed experiments and analyses on WebQSP verify the effectiveness of SKP, especially the significant improvement in subgraph retrieval (+4.08% H@10).","url_abs":"https://arxiv.org/abs/2308.14436v1","url_pdf":"https://arxiv.org/pdf/2308.14436v1.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":"bridging-the-kb-text-gap-leveraging","repo_url":"https://github.com/dongguanting/skp-for-kbqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"knowledge-base-question-answering","task_name":"Knowledge Base Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/knowledge-base-question-answering-on-1","task":"Knowledge Base Question Answering","dataset":"WebQuestionsSP","model":"SKP","rank_in_archive_order":3,"of":8,"metrics":{"Hits@1":"79.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.14436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14436"}},"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/dongguanting/skp-for-kbqa","reach":{"status":"ok"}}],"summary":{"ran":10},"by_repo_kind":{"official":{"samples":10,"ran":10,"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":10,"samples":[{"code_sha256_prefix":"9377eb8058dfa617","entry":"default_data_collator","repo":"dongguanting/skp-for-kbqa","repo_kind":"official","path":"DPR_pretraining/data_collactor.py","file_url":"https://github.com/dongguanting/skp-for-kbqa/blob/HEAD/DPR_pretraining/data_collactor.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":"9377eb8058dfa617"}},{"code_sha256_prefix":"e671c895df132135","entry":"get_answers","repo":"dongguanting/skp-for-kbqa","repo_kind":"official","path":"DPR_inference/fid_preprocess.py","file_url":"https://github.com/dongguanting/skp-for-kbqa/blob/HEAD/DPR_inference/fid_preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e671c895df132135"}},{"code_sha256_prefix":"24a0d889f41f7882","entry":"get_entities","repo":"dongguanting/skp-for-kbqa","repo_kind":"official","path":"DPR_inference/fid_preprocess.py","file_url":"https://github.com/dongguanting/skp-for-kbqa/blob/HEAD/DPR_inference/fid_preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"24a0d889f41f7882"}},{"code_sha256_prefix":"76e71b6742137d91","entry":"get_fid","repo":"dongguanting/skp-for-kbqa","repo_kind":"official","path":"DPR_inference/fid_preprocess.py","file_url":"https://github.com/dongguanting/skp-for-kbqa/blob/HEAD/DPR_inference/fid_preprocess.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":"76e71b6742137d91"}},{"code_sha256_prefix":"0f18cce9ec62f6e6","entry":"list_to_str","repo":"dongguanting/skp-for-kbqa","repo_kind":"official","path":"DPR_pretraining/main_bert.py","file_url":"https://github.com/dongguanting/skp-for-kbqa/blob/HEAD/DPR_pretraining/main_bert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0f18cce9ec62f6e6"}},{"code_sha256_prefix":"5a6dd8868629358f","entry":"mask_mask","repo":"dongguanting/skp-for-kbqa","repo_kind":"official","path":"DPR-main/train_dense_encoder_mask.py","file_url":"https://github.com/dongguanting/skp-for-kbqa/blob/HEAD/DPR-main/train_dense_encoder_mask.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a6dd8868629358f"}},{"code_sha256_prefix":"39eb9ce1e34b3d1c","entry":"ner_mask","repo":"dongguanting/skp-for-kbqa","repo_kind":"official","path":"DPR_pretraining/main_bert.py","file_url":"https://github.com/dongguanting/skp-for-kbqa/blob/HEAD/DPR_pretraining/main_bert.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":"39eb9ce1e34b3d1c"}},{"code_sha256_prefix":"87d6dbae98f9c70a","entry":"ner_preprocess","repo":"dongguanting/skp-for-kbqa","repo_kind":"official","path":"DPR_pretraining/main_bert.py","file_url":"https://github.com/dongguanting/skp-for-kbqa/blob/HEAD/DPR_pretraining/main_bert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"87d6dbae98f9c70a"}},{"code_sha256_prefix":"899f3144b20efb88","entry":"tf_default_data_collator","repo":"dongguanting/skp-for-kbqa","repo_kind":"official","path":"DPR_pretraining/data_collactor.py","file_url":"https://github.com/dongguanting/skp-for-kbqa/blob/HEAD/DPR_pretraining/data_collactor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"899f3144b20efb88"}},{"code_sha256_prefix":"0e912aec22029af8","entry":"torch_default_data_collator","repo":"dongguanting/skp-for-kbqa","repo_kind":"official","path":"DPR_pretraining/data_collactor.py","file_url":"https://github.com/dongguanting/skp-for-kbqa/blob/HEAD/DPR_pretraining/data_collactor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e912aec22029af8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}