Papers › RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

14 May 2022arXiv:2205.06983archive 2025-07-28

Jiexing Qi, Jingyao Tang, Ziwei He, Xiangpeng Wan, Yu Cheng, Chenghu Zhou, Xinbing Wang, Quanshi Zhang, Zhouhan Lin

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).

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 9 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lumia-group/rasat officialmentioned in paperpytorchApache-2.0Syntology: 9 samples, 5 ran (0 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran
4unverified

Licence: 1 of the 9 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from lumia-group/rasat. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives 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” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

lumia-group/rasat official repository 9 samples, 5 ran (0 instrument-failed) · 4 unverified
find_turn_idx get_coref.py ran Apache-2.0 (permissive) · f40c5b19a5755c5e · report fixture: signature id:int/0/int, turn_list:list/1/str, len_text_list:list/1/int · returned tuple · level recorded 2026-09-24
get_column_compact_list seq2seq/preprocess/align_tables.py ran Apache-2.0 (permissive) · ef08ebed19d53e89 · report fixture: signature load_dict_item:list/1/tuple · returned list · level recorded 2026-09-24
isSame seq2seq/preprocess/align_tables.py ran fingerprinted Apache-2.0 (permissive) · 7a488955ab0677f4 · report fixture: signature ori_text:str/0/str, text:str/0/str · returned bool · level recorded 2026-09-24
quote_normalization get_coref.py ran Apache-2.0 (permissive) · 80f6c321b64857ef · report fixture: signature dataset_name:str/0/str, data_idx:int/0/int, question:list/1/str · returned list · level recorded 2026-09-24
recovery_from_compact_list seq2seq/preprocess/align_tables.py ran Apache-2.0 (permissive) · 2a28bd560ba40e78 · report fixture: signature compact_list:list/1/list · returned list · level recorded 2026-09-24
get_original_t5_model seq2seq/model/model_utils.py unverified Apache-2.0 (permissive) · 54c49cad4c3a3dcd · report
get_relation_t5_model seq2seq/model/model_utils.py unverified Apache-2.0 (permissive) · 2e9ce4d146135d4b · report
load_tf_weights_in_t5 in 28 papers seq2seq/model/t5_original_model.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 136abfa3e8ce028d · report
preprocess_by_dataset seq2seq/preprocess/choose_dataset.py unverified Apache-2.0 (permissive) · f43342e041f67e98 · report

Tasks

Dialogue State TrackingSemantic ParsingText to SQLText-To-SQL

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dialogue State Tracking CoSQL RASAT+PICARD interaction match accuracy 26.5 #1 of 9 Archive leaderboard report
Dialogue State Tracking CoSQL RASAT+PICARD question match accuracy 55.7 #1 of 9 Archive leaderboard report
Semantic Parsing spider RASAT+PICARD Accuracy 75.5 #3 of 10 Archive leaderboard report
Text-To-SQL SPIDER RASAT+PICARD Exact Match Accuracy (in Dev) 75.3 #2 of 4 Archive leaderboard report
Text-To-SQL SPIDER RASAT+PICARD Execution Accuracy (in Dev) 80.5 #2 of 4 Archive leaderboard report
Text-To-SQL SPIDER RASAT Exact Match Accuracy (in Dev) 72.6 #3 of 4 Archive leaderboard report
Text-To-SQL SPIDER RASAT Execution Accuracy (in Dev) 76.6 #3 of 4 Archive leaderboard report
Text-To-SQL SParC RASAT+PICARD interaction match accuracy 45.2 #1 of 7 Archive leaderboard report
Text-To-SQL SParC RASAT+PICARD question match accuracy 67.7 #1 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdafactorAdamAttentionAttention DropoutBPEDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLSTMLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSentencePieceSeq2SeqSigmoid ActivationSoftmaxT5Tanh ActivationTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections