{"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/table-retrieval-may-not-necessitate-table","title":"Table Retrieval May Not Necessitate Table-specific Model Design","arxiv_id":"2205.09843","date":"2022-05-19","proceeding":"NAACL (SUKI) 2022 7","authors":["Zhiruo Wang","Zhengbao Jiang","Eric Nyberg","Graham Neubig"],"abstract":"Tables are an important form of structured data for both human and machine readers alike, providing answers to questions that cannot, or cannot easily, be found in texts. Recent work has designed special models and training paradigms for table-related tasks such as table-based question answering and table retrieval. Though effective, they add complexity in both modeling and data acquisition compared to generic text solutions and obscure which elements are truly beneficial. In this work, we focus on the task of table retrieval, and ask: \"is table-specific model design necessary for table retrieval, or can a simpler text-based model be effectively used to achieve a similar result?\" First, we perform an analysis on a table-based portion of the Natural Questions dataset (NQ-table), and find that structure plays a negligible role in more than 70% of the cases. Based on this, we experiment with a general Dense Passage Retriever (DPR) based on text and a specialized Dense Table Retriever (DTR) that uses table-specific model designs. We find that DPR performs well without any table-specific design and training, and even achieves superior results compared to DTR when fine-tuned on properly linearized tables. We then experiment with three modules to explicitly encode table structures, namely auxiliary row/column embeddings, hard attention masks, and soft relation-based attention biases. However, none of these yielded significant improvements, suggesting that table-specific model design may not be necessary for table retrieval.","url_abs":"https://arxiv.org/abs/2205.09843v1","url_pdf":"https://arxiv.org/pdf/2205.09843v1.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":"table-retrieval-may-not-necessitate-table","repo_url":"https://github.com/zorazrw/nqt-retrieval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hard-attention","task_name":"Hard Attention"},{"task_slug":"natural-questions","task_name":"Natural Questions"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"table-retrieval","task_name":"Table Retrieval"},{"task_slug":"table-based-question-answering","task_name":"Table-based Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.09843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09843"}},"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/zorazrw/nqt-retrieval","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"ran":4,"unverified":5},"by_repo_kind":{"official":{"samples":12,"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":"928414780ee23e45","entry":"dot_product_scores","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"dpr/models/biencoder.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/dpr/models/biencoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"928414780ee23e45"}},{"code_sha256_prefix":"1df81ea9d2da7b70","entry":"compute_loss","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"dpr/models/reader.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/dpr/models/reader.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1df81ea9d2da7b70"}},{"code_sha256_prefix":"4c7d079ed8d8dd58","entry":"cosine_scores","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"dpr/models/biencoder.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/dpr/models/biencoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c7d079ed8d8dd58"}},{"code_sha256_prefix":"70967062c0b97377","entry":"get_encoder_params_state_from_cfg","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"dpr/options.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/dpr/options.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70967062c0b97377"}},{"code_sha256_prefix":"f754a83bdbe3d5ed","entry":"move_to_cuda","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"dpr/utils/model_utils.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/dpr/utils/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f754a83bdbe3d5ed"}},{"code_sha256_prefix":"5ef6dc01ca2773cb","entry":"move_to_device","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"dpr/utils/model_utils.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/dpr/utils/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ef6dc01ca2773cb"}},{"code_sha256_prefix":"5964d1c902593444","entry":"setup_cfg_gpu","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"dpr/options.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/dpr/options.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5964d1c902593444"}},{"code_sha256_prefix":"0c6cadd319db2130","entry":"get_annotated_table_ids","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"convert_data.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/convert_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c6cadd319db2130"}},{"code_sha256_prefix":"a7d60264a4371491","entry":"load_tables_dict","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"convert_data.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/convert_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a7d60264a4371491"}},{"code_sha256_prefix":"acb496d6cacbc58f","entry":"setup_for_distributed_mode","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"dpr/utils/model_utils.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/dpr/utils/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"acb496d6cacbc58f"}},{"code_sha256_prefix":"b4bc9c9849591a70","entry":"shuffle_nq_table_by_column","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"process_table.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/process_table.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b4bc9c9849591a70"}},{"code_sha256_prefix":"71d9b6ee2c505c02","entry":"shuffle_nq_table_by_row","repo":"zorazrw/nqt-retrieval","repo_kind":"official","path":"process_table.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/process_table.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71d9b6ee2c505c02"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}