{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/rasat-integrating-relational-structures-into","title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","arxiv_id":"2205.06983","date":"2022-05-14","proceeding":null,"authors":["Jiexing Qi","Jingyao Tang","Ziwei He","Xiangpeng Wan","Yu Cheng","Chenghu Zhou","Xinbing Wang","Quanshi Zhang","Zhouhan Lin"],"abstract":"Relational structures such as schema linking and schema encoding have been validated as a key component to qualitatively translating natural language into SQL queries. However, introducing these structural relations comes with prices: they often result in a specialized model structure, which largely prohibits using large pretrained models in text-to-SQL. To address this problem, we propose RASAT: a Transformer seq2seq architecture augmented with relation-aware self-attention that could leverage a variety of relational structures while inheriting the pretrained parameters from the T5 model effectively. Our model can incorporate almost all types of existing relations in the literature, and in addition, we propose introducing co-reference relations for the multi-turn scenario. Experimental results on three widely used text-to-SQL datasets, covering both single-turn and multi-turn scenarios, have shown that RASAT could achieve state-of-the-art results across all three benchmarks (75.5% EX on Spider, 52.6% IEX on SParC, and 37.4% IEX on CoSQL).","url_abs":"https://arxiv.org/abs/2205.06983v2","url_pdf":"https://arxiv.org/pdf/2205.06983v2.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":"rasat-integrating-relational-structures-into","repo_url":"https://github.com/lumia-group/rasat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"dialogue-state-tracking","task_name":"Dialogue State Tracking"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"text-to-sql","task_name":"Text to SQL"},{"task_slug":"text-to-sql","task_name":"Text-To-SQL"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dialogue-state-tracking-on-cosql","task":"Dialogue State Tracking","dataset":"CoSQL","model":"RASAT+PICARD","rank_in_archive_order":1,"of":9,"metrics":{"interaction match accuracy":"26.5","question match accuracy":"55.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-parsing-on-spider","task":"Semantic Parsing","dataset":"spider","model":"RASAT+PICARD","rank_in_archive_order":3,"of":10,"metrics":{"Accuracy":"75.5"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-sql-on-spider-1","task":"Text-To-SQL","dataset":"SPIDER","model":"RASAT+PICARD","rank_in_archive_order":2,"of":4,"metrics":{"Exact Match Accuracy (in Dev)":"75.3","Execution Accuracy (in Dev)":"80.5"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-sql-on-spider-1","task":"Text-To-SQL","dataset":"SPIDER","model":"RASAT","rank_in_archive_order":3,"of":4,"metrics":{"Exact Match Accuracy (in Dev)":"72.6","Execution Accuracy (in Dev)":"76.6"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-sql-on-sparc","task":"Text-To-SQL","dataset":"SParC","model":"RASAT+PICARD","rank_in_archive_order":1,"of":7,"metrics":{"interaction match accuracy":"45.2","question match accuracy":"67.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.06983","atlas_url":"https://app.syntology.ai/?focus=2205.06983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.06983"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2205.06983"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2205.06983"},"call":"get_harvested_code_for_paper(arxiv_id=\"2205.06983\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2205.06983"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.06983\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.06983"},"call":"get_concepts_for_paper(arxiv_id=\"2205.06983\")"}],"by_repo":[{"repo":"lumia-group/rasat","kind":"official","samples":9,"ran":5,"instrument":0,"unverified":4}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2205.06983.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2205.06983.svg"},"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/lumia-group/rasat","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":4},"n_samples":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":9,"ran":5,"n_ran_checked":5,"n_instrument":0,"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":1,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":1,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"f40c5b19a5755c5e","code_sha256_prefix":"f40c5b19a5755c5e","entry":"find_turn_idx","repo":"lumia-group/rasat","repo_kind":"official","path":"get_coref.py","file_url":"https://github.com/lumia-group/rasat/blob/HEAD/get_coref.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"id:int/0/int, turn_list:list/1/str, len_text_list:list/1/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f40c5b19a5755c5e"}},{"code_sha256":"ef08ebed19d53e89","code_sha256_prefix":"ef08ebed19d53e89","entry":"get_column_compact_list","repo":"lumia-group/rasat","repo_kind":"official","path":"seq2seq/preprocess/align_tables.py","file_url":"https://github.com/lumia-group/rasat/blob/HEAD/seq2seq/preprocess/align_tables.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"load_dict_item:list/1/tuple","fixture_out_type":"list","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ef08ebed19d53e89"}},{"code_sha256":"7a488955ab0677f4","code_sha256_prefix":"7a488955ab0677f4","entry":"isSame","repo":"lumia-group/rasat","repo_kind":"official","path":"seq2seq/preprocess/align_tables.py","file_url":"https://github.com/lumia-group/rasat/blob/HEAD/seq2seq/preprocess/align_tables.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"ori_text:str/0/str, text:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7a488955ab0677f4"},"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7a488955ab0677f4"}},{"code_sha256":"80f6c321b64857ef","code_sha256_prefix":"80f6c321b64857ef","entry":"quote_normalization","repo":"lumia-group/rasat","repo_kind":"official","path":"get_coref.py","file_url":"https://github.com/lumia-group/rasat/blob/HEAD/get_coref.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"dataset_name:str/0/str, data_idx:int/0/int, question:list/1/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"80f6c321b64857ef"}},{"code_sha256":"2a28bd560ba40e78","code_sha256_prefix":"2a28bd560ba40e78","entry":"recovery_from_compact_list","repo":"lumia-group/rasat","repo_kind":"official","path":"seq2seq/preprocess/align_tables.py","file_url":"https://github.com/lumia-group/rasat/blob/HEAD/seq2seq/preprocess/align_tables.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"compact_list:list/1/list","fixture_out_type":"list","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2a28bd560ba40e78"}},{"code_sha256":"54c49cad4c3a3dcd","code_sha256_prefix":"54c49cad4c3a3dcd","entry":"get_original_t5_model","repo":"lumia-group/rasat","repo_kind":"official","path":"seq2seq/model/model_utils.py","file_url":"https://github.com/lumia-group/rasat/blob/HEAD/seq2seq/model/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"54c49cad4c3a3dcd"}},{"code_sha256":"2e9ce4d146135d4b","code_sha256_prefix":"2e9ce4d146135d4b","entry":"get_relation_t5_model","repo":"lumia-group/rasat","repo_kind":"official","path":"seq2seq/model/model_utils.py","file_url":"https://github.com/lumia-group/rasat/blob/HEAD/seq2seq/model/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2e9ce4d146135d4b"}},{"code_sha256":"136abfa3e8ce028d","code_sha256_prefix":"136abfa3e8ce028d","entry":"load_tf_weights_in_t5","repo":"lumia-group/rasat","repo_kind":"official","path":"seq2seq/model/t5_original_model.py","file_url":"https://github.com/lumia-group/rasat/blob/HEAD/seq2seq/model/t5_original_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/load-tf-weights-in-t5","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from suntea233/DualLoRA, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"136abfa3e8ce028d"}},{"code_sha256":"f43342e041f67e98","code_sha256_prefix":"f43342e041f67e98","entry":"preprocess_by_dataset","repo":"lumia-group/rasat","repo_kind":"official","path":"seq2seq/preprocess/choose_dataset.py","file_url":"https://github.com/lumia-group/rasat/blob/HEAD/seq2seq/preprocess/choose_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f43342e041f67e98"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c64fdb70622b78fa39557f621f7ded47724dbba7ea92c358b6eb0272dbbb9b31","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}