{"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/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":null,"atlas_url":"https://app.syntology.ai/?focus=2205.06983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.06983"}},"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/lumia-group/rasat","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":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":0,"samples":[{"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":"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":"f40c5b19a5755c5e"}},{"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":"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":"ef08ebed19d53e89"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"54c49cad4c3a3dcd"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2e9ce4d146135d4b"}},{"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":"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":"7a488955ab0677f4"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"136abfa3e8ce028d"}},{"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,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f43342e041f67e98"}},{"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":"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":"80f6c321b64857ef"}},{"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":"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":"2a28bd560ba40e78"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}