UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQL Article Swipe
Longxu Dou
,
Yan Gao
,
Mingyang Pan
,
Dingzirui Wang
,
Jian–Guang Lou
,
Wanxiang Che
,
Dechen Zhan
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2203.07781
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2203.07781
Existing text-to-SQL semantic parsers are typically designed for particular settings such as handling queries that span multiple tables, domains or turns which makes them ineffective when applied to different settings. We present UniSAr (Unified Structure-Aware Autoregressive Language Model), which benefits from directly using an off-the-shelf language model architecture and demonstrates consistently high performance under different settings. Specifically, UniSAr extends existing autoregressive language models to incorporate three non-invasive extensions to make them structure-aware: (1) adding structure mark to encode database schema, conversation context, and their relationships; (2) constrained decoding to decode well structured SQL for a given database schema; and (3) SQL completion to complete potential missing JOIN relationships in SQL based on database schema. On seven well-known text-to-SQL datasets covering multi-domain, multi-table and multi-turn, UniSAr demonstrates highly comparable or better performance to the most advanced specifically-designed text-to-SQL models. Importantly, our UniSAr is non-invasive, such that other core model advances in text-to-SQL can also adopt our extensions to further enhance performance.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2203.07781
- https://arxiv.org/pdf/2203.07781
- OA Status
- green
- Cited By
- 7
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4221166881
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4221166881Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2203.07781Digital Object Identifier
- Title
-
UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQLWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-03-15Full publication date if available
- Authors
-
Longxu Dou, Yan Gao, Mingyang Pan, Dingzirui Wang, Jian–Guang Lou, Wanxiang Che, Dechen ZhanList of authors in order
- Landing page
-
https://arxiv.org/abs/2203.07781Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2203.07781Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2203.07781Direct OA link when available
- Concepts
-
Computer science, SQL, Data definition language, Schema (genetic algorithms), Programming language, Natural language processing, Artificial intelligence, Database, Information retrievalTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
7Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1, 2023: 4, 2022: 2Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4221166881 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2203.07781 |
| ids.doi | https://doi.org/10.48550/arxiv.2203.07781 |
| ids.openalex | https://openalex.org/W4221166881 |
| fwci | |
| type | preprint |
| title | UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQL |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9962999820709229 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Topic Modeling |
| topics[1].id | https://openalex.org/T10181 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9941999912261963 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Natural Language Processing Techniques |
| topics[2].id | https://openalex.org/T10215 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.917900025844574 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Semantic Web and Ontologies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8790684342384338 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C510870499 |
| concepts[1].level | 2 |
| concepts[1].score | 0.8069272041320801 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q47607 |
| concepts[1].display_name | SQL |
| concepts[2].id | https://openalex.org/C55596503 |
| concepts[2].level | 3 |
| concepts[2].score | 0.6977089047431946 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1431648 |
| concepts[2].display_name | Data definition language |
| concepts[3].id | https://openalex.org/C52146309 |
| concepts[3].level | 2 |
| concepts[3].score | 0.4842550456523895 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q7431116 |
| concepts[3].display_name | Schema (genetic algorithms) |
| concepts[4].id | https://openalex.org/C199360897 |
| concepts[4].level | 1 |
| concepts[4].score | 0.45639628171920776 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[4].display_name | Programming language |
| concepts[5].id | https://openalex.org/C204321447 |
| concepts[5].level | 1 |
| concepts[5].score | 0.37172621488571167 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[5].display_name | Natural language processing |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.3564482033252716 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C77088390 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3270811438560486 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q8513 |
| concepts[7].display_name | Database |
| concepts[8].id | https://openalex.org/C23123220 |
| concepts[8].level | 1 |
| concepts[8].score | 0.2634792923927307 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q816826 |
| concepts[8].display_name | Information retrieval |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8790684342384338 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/sql |
| keywords[1].score | 0.8069272041320801 |
| keywords[1].display_name | SQL |
| keywords[2].id | https://openalex.org/keywords/data-definition-language |
| keywords[2].score | 0.6977089047431946 |
| keywords[2].display_name | Data definition language |
| keywords[3].id | https://openalex.org/keywords/schema |
| keywords[3].score | 0.4842550456523895 |
| keywords[3].display_name | Schema (genetic algorithms) |
| keywords[4].id | https://openalex.org/keywords/programming-language |
| keywords[4].score | 0.45639628171920776 |
| keywords[4].display_name | Programming language |
| keywords[5].id | https://openalex.org/keywords/natural-language-processing |
| keywords[5].score | 0.37172621488571167 |
| keywords[5].display_name | Natural language processing |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.3564482033252716 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/database |
| keywords[7].score | 0.3270811438560486 |
| keywords[7].display_name | Database |
| keywords[8].id | https://openalex.org/keywords/information-retrieval |
| keywords[8].score | 0.2634792923927307 |
| keywords[8].display_name | Information retrieval |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2203.07781 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2203.07781 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2203.07781 |
| locations[1].id | doi:10.48550/arxiv.2203.07781 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2203.07781 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5039847345 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Longxu Dou |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Dou, Longxu |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100462451 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3295-5755 |
| authorships[1].author.display_name | Yan Gao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Gao, Yan |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5063170334 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1327-6105 |
| authorships[2].author.display_name | Mingyang Pan |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Pan, Mingyang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5000300840 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Dingzirui Wang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Wang, Dingzirui |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5025118710 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Jian–Guang Lou |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Lou, Jian-Guang |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5019108029 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-3907-0335 |
| authorships[5].author.display_name | Wanxiang Che |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Che, Wanxiang |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5113748483 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Dechen Zhan |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Zhan, Dechen |
| authorships[6].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2203.07781 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-04-03T00:00:00 |
| display_name | UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQL |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9962999820709229 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Topic Modeling |
| related_works | https://openalex.org/W1592149428, https://openalex.org/W650213220, https://openalex.org/W1980548249, https://openalex.org/W2183714398, https://openalex.org/W3094396153, https://openalex.org/W2042813897, https://openalex.org/W2340883001, https://openalex.org/W4382050951, https://openalex.org/W2079321164, https://openalex.org/W1554917839 |
| cited_by_count | 7 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 4 |
| counts_by_year[2].year | 2022 |
| counts_by_year[2].cited_by_count | 2 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2203.07781 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2203.07781 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2203.07781 |
| primary_location.id | pmh:oai:arXiv.org:2203.07781 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2203.07781 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2203.07781 |
| publication_date | 2022-03-15 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 94 |
| abstract_inverted_index.On | 114 |
| abstract_inverted_index.We | 30 |
| abstract_inverted_index.an | 43 |
| abstract_inverted_index.as | 11 |
| abstract_inverted_index.in | 108, 149 |
| abstract_inverted_index.is | 141 |
| abstract_inverted_index.on | 111 |
| abstract_inverted_index.or | 19, 128 |
| abstract_inverted_index.to | 27, 63, 68, 76, 88, 102, 131, 156 |
| abstract_inverted_index.(1) | 72 |
| abstract_inverted_index.(2) | 85 |
| abstract_inverted_index.(3) | 99 |
| abstract_inverted_index.SQL | 92, 100, 109 |
| abstract_inverted_index.and | 48, 82, 98, 122 |
| abstract_inverted_index.are | 4 |
| abstract_inverted_index.can | 151 |
| abstract_inverted_index.for | 7, 93 |
| abstract_inverted_index.our | 139, 154 |
| abstract_inverted_index.the | 132 |
| abstract_inverted_index.JOIN | 106 |
| abstract_inverted_index.also | 152 |
| abstract_inverted_index.core | 146 |
| abstract_inverted_index.from | 40 |
| abstract_inverted_index.high | 51 |
| abstract_inverted_index.make | 69 |
| abstract_inverted_index.mark | 75 |
| abstract_inverted_index.most | 133 |
| abstract_inverted_index.span | 15 |
| abstract_inverted_index.such | 10, 143 |
| abstract_inverted_index.that | 14, 144 |
| abstract_inverted_index.them | 23, 70 |
| abstract_inverted_index.well | 90 |
| abstract_inverted_index.when | 25 |
| abstract_inverted_index.adopt | 153 |
| abstract_inverted_index.based | 110 |
| abstract_inverted_index.given | 95 |
| abstract_inverted_index.makes | 22 |
| abstract_inverted_index.model | 46, 147 |
| abstract_inverted_index.other | 145 |
| abstract_inverted_index.seven | 115 |
| abstract_inverted_index.their | 83 |
| abstract_inverted_index.three | 65 |
| abstract_inverted_index.turns | 20 |
| abstract_inverted_index.under | 53 |
| abstract_inverted_index.using | 42 |
| abstract_inverted_index.which | 21, 38 |
| abstract_inverted_index.UniSAr | 32, 57, 124, 140 |
| abstract_inverted_index.adding | 73 |
| abstract_inverted_index.better | 129 |
| abstract_inverted_index.decode | 89 |
| abstract_inverted_index.encode | 77 |
| abstract_inverted_index.highly | 126 |
| abstract_inverted_index.models | 62 |
| abstract_inverted_index.Model), | 37 |
| abstract_inverted_index.applied | 26 |
| abstract_inverted_index.domains | 18 |
| abstract_inverted_index.enhance | 158 |
| abstract_inverted_index.extends | 58 |
| abstract_inverted_index.further | 157 |
| abstract_inverted_index.missing | 105 |
| abstract_inverted_index.models. | 137 |
| abstract_inverted_index.parsers | 3 |
| abstract_inverted_index.present | 31 |
| abstract_inverted_index.queries | 13 |
| abstract_inverted_index.schema, | 79 |
| abstract_inverted_index.schema. | 113 |
| abstract_inverted_index.schema; | 97 |
| abstract_inverted_index.tables, | 17 |
| abstract_inverted_index.(Unified | 33 |
| abstract_inverted_index.Existing | 0 |
| abstract_inverted_index.Language | 36 |
| abstract_inverted_index.advanced | 134 |
| abstract_inverted_index.advances | 148 |
| abstract_inverted_index.benefits | 39 |
| abstract_inverted_index.complete | 103 |
| abstract_inverted_index.context, | 81 |
| abstract_inverted_index.covering | 119 |
| abstract_inverted_index.database | 78, 96, 112 |
| abstract_inverted_index.datasets | 118 |
| abstract_inverted_index.decoding | 87 |
| abstract_inverted_index.designed | 6 |
| abstract_inverted_index.directly | 41 |
| abstract_inverted_index.existing | 59 |
| abstract_inverted_index.handling | 12 |
| abstract_inverted_index.language | 45, 61 |
| abstract_inverted_index.multiple | 16 |
| abstract_inverted_index.semantic | 2 |
| abstract_inverted_index.settings | 9 |
| abstract_inverted_index.different | 28, 54 |
| abstract_inverted_index.potential | 104 |
| abstract_inverted_index.settings. | 29, 55 |
| abstract_inverted_index.structure | 74 |
| abstract_inverted_index.typically | 5 |
| abstract_inverted_index.comparable | 127 |
| abstract_inverted_index.completion | 101 |
| abstract_inverted_index.extensions | 67, 155 |
| abstract_inverted_index.particular | 8 |
| abstract_inverted_index.structured | 91 |
| abstract_inverted_index.well-known | 116 |
| abstract_inverted_index.constrained | 86 |
| abstract_inverted_index.incorporate | 64 |
| abstract_inverted_index.ineffective | 24 |
| abstract_inverted_index.multi-table | 121 |
| abstract_inverted_index.multi-turn, | 123 |
| abstract_inverted_index.performance | 52, 130 |
| abstract_inverted_index.text-to-SQL | 1, 117, 136, 150 |
| abstract_inverted_index.Importantly, | 138 |
| abstract_inverted_index.architecture | 47 |
| abstract_inverted_index.consistently | 50 |
| abstract_inverted_index.conversation | 80 |
| abstract_inverted_index.demonstrates | 49, 125 |
| abstract_inverted_index.non-invasive | 66 |
| abstract_inverted_index.performance. | 159 |
| abstract_inverted_index.Specifically, | 56 |
| abstract_inverted_index.multi-domain, | 120 |
| abstract_inverted_index.non-invasive, | 142 |
| abstract_inverted_index.off-the-shelf | 44 |
| abstract_inverted_index.relationships | 107 |
| abstract_inverted_index.Autoregressive | 35 |
| abstract_inverted_index.autoregressive | 60 |
| abstract_inverted_index.relationships; | 84 |
| abstract_inverted_index.Structure-Aware | 34 |
| abstract_inverted_index.structure-aware: | 71 |
| abstract_inverted_index.specifically-designed | 135 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.5199999809265137 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |