{"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/knowledge-guided-text-retrieval-and-reading","title":"Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering","arxiv_id":"1911.03868","date":"2019-11-10","proceeding":null,"authors":["Sewon Min","Danqi Chen","Luke Zettlemoyer","Hannaneh Hajishirzi"],"abstract":"We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or co-occurrence in the same article. Our goals are to boost coverage by using knowledge-guided retrieval to find more relevant passages than text-matching methods, and to improve accuracy by allowing for better knowledge-guided fusion of information across related passages. Our graph retrieval method expands a set of seed keyword-retrieved passages by traversing the graph structure of the knowledge base. Our reader extends a BERT-based architecture and updates passage representations by propagating information from related passages and their relations, instead of reading each passage in isolation. Experiments on three open-domain QA datasets, WebQuestions, Natural Questions and TriviaQA, show improved performance over non-graph baselines by 2-11% absolute. Our approach also matches or exceeds the state-of-the-art in every case, without using an expensive end-to-end training regime.","url_abs":"https://arxiv.org/abs/1911.03868v2","url_pdf":"https://arxiv.org/pdf/1911.03868v2.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":"knowledge-guided-text-retrieval-and-reading","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"knowledge-guided-text-retrieval-and-reading","repo_url":"https://github.com/facebookresearch/DPR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"knowledge-guided-text-retrieval-and-reading","repo_url":"https://github.com/hongyuntw/DPR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"knowledge-guided-text-retrieval-and-reading","repo_url":"https://github.com/hongyuntw/DPR_BESS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"knowledge-guided-text-retrieval-and-reading","repo_url":"https://github.com/nidhikamal-emb/DPR_repo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"knowledge-guided-text-retrieval-and-reading","repo_url":"https://github.com/shmsw25/GraphRetriever","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"knowledge-guided-text-retrieval-and-reading","repo_url":"https://github.com/Heidelberg-NLP/discourse-aware-semantic-self-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"natural-questions","task_name":"Natural Questions"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-matching","task_name":"Text Matching"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"triviaqa","task_name":"TriviaQA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.03868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03868"}},"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/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shmsw25/GraphRetriever","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Heidelberg-NLP/discourse-aware-semantic-self-attention","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hongyuntw/DPR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/DPR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hongyuntw/DPR_BESS","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nidhikamal-emb/DPR_repo","reach":null}],"summary":{"ran_draft_wrong":4,"unverified":2},"by_repo_kind":{"listed":{"samples":4,"ran":2,"repositories":3}},"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":4,"samples":[{"code_sha256_prefix":"928414780ee23e45","entry":"dot_product_scores","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":"928414780ee23e45"}},{"code_sha256_prefix":"4c7d079ed8d8dd58","entry":"cosine_scores","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":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"4c7d079ed8d8dd58"}},{"code_sha256_prefix":"e60834120b9256f9","entry":"load_passages","repo":"hongyuntw/DPR","repo_kind":"listed","path":"dense_retriever.py","file_url":"https://github.com/hongyuntw/DPR/blob/HEAD/dense_retriever.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e60834120b9256f9"}},{"code_sha256_prefix":"dae7ab386661a4f4","entry":"normalize_answer","repo":"shmsw25/GraphRetriever","repo_kind":"listed","path":"WikiData.py","file_url":"https://github.com/shmsw25/GraphRetriever/blob/HEAD/WikiData.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dae7ab386661a4f4"}},{"code_sha256_prefix":"54a1759eb619f749","entry":"attentions_to_json","repo":"Heidelberg-NLP/discourse-aware-semantic-self-attention","repo_kind":"listed","path":"docqa/commands/evaluate_qanet_semantic_flat.py","file_url":"https://github.com/Heidelberg-NLP/discourse-aware-semantic-self-attention/blob/HEAD/docqa/commands/evaluate_qanet_semantic_flat.py","link_basis":"harvester_set","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":"54a1759eb619f749"}},{"code_sha256_prefix":"9cecf482ef0508aa","entry":"create_argparse_namespace","repo":"Heidelberg-NLP/discourse-aware-semantic-self-attention","repo_kind":"listed","path":"docqa/commands/evaluate_qanet_semantic_flat.py","file_url":"https://github.com/Heidelberg-NLP/discourse-aware-semantic-self-attention/blob/HEAD/docqa/commands/evaluate_qanet_semantic_flat.py","link_basis":"harvester_set","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":"9cecf482ef0508aa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}