{"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/picard-parsing-incrementally-for-constrained","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","arxiv_id":"2109.05093","date":"2021-09-10","proceeding":"EMNLP 2021 11","authors":["Torsten Scholak","Nathan Schucher","Dzmitry Bahdanau"],"abstract":"Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of 10,000s of sub-word tokens. When fine-tuned to target constrained formal languages like SQL, these models often generate invalid code, rendering it unusable. We propose PICARD (code and trained models available at https://github.com/ElementAI/picard), a method for constraining auto-regressive decoders of language models through incremental parsing. PICARD helps to find valid output sequences by rejecting inadmissible tokens at each decoding step. On the challenging Spider and CoSQL text-to-SQL translation tasks, we show that PICARD transforms fine-tuned T5 models with passable performance into state-of-the-art solutions.","url_abs":"https://arxiv.org/abs/2109.05093v1","url_pdf":"https://arxiv.org/pdf/2109.05093v1.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":"picard-parsing-incrementally-for-constrained","repo_url":"https://github.com/ElementAI/picard","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"picard-parsing-incrementally-for-constrained","repo_url":"https://github.com/servicenow/picard","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"picard-parsing-incrementally-for-constrained","repo_url":"https://github.com/yangyucheng000/Paper-3/tree/main/acm-mm-2023-picr-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"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"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"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":"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":"picard","method_name":"PICARD"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"}],"datasets_introduced":[],"methods_introduced":[{"slug":"picard","name":"PICARD","full_name":"Parsing Incrementally for Constrained Auto-Regressive Decoding"}],"results":[{"leaderboard":"/sota/dialogue-state-tracking-on-cosql","task":"Dialogue State Tracking","dataset":"CoSQL","model":"T5-3B + PICARD","rank_in_archive_order":2,"of":9,"metrics":{"interaction match accuracy":"23.7","question match accuracy":"54.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-parsing-on-spider","task":"Semantic Parsing","dataset":"spider","model":"T5-3B + PICARD","rank_in_archive_order":5,"of":10,"metrics":{"Accuracy":"71.9 "},"uses_additional_data":false},{"leaderboard":"/sota/text-to-sql-on-spider-1","task":"Text-To-SQL","dataset":"SPIDER","model":"T5-3B+PICARD","rank_in_archive_order":1,"of":4,"metrics":{"Exact Match Accuracy (in Dev)":"75.5","Execution Accuracy (in Dev)":"79.3"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-sql-on-spider-1","task":"Text-To-SQL","dataset":"SPIDER","model":"T5-3B","rank_in_archive_order":4,"of":4,"metrics":{"Exact Match Accuracy (in Dev)":"71.5","Execution Accuracy (in Dev)":"74.4"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-sql-on-spider","task":"Text-To-SQL","dataset":"spider","model":"T5-3B + PICARD","rank_in_archive_order":12,"of":20,"metrics":{"Exact Match Accuracy (Dev)":"75.5","Exact Match Accuracy (Test)":"71.9 ","Execution Accuracy (Test)":"75.1"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2109.05093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05093"}},"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/yangyucheng000/Paper-3/tree/main/acm-mm-2023-picr-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/servicenow/picard","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ElementAI/picard","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":4,"repositories":1},"listed":{"samples":1,"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":"b724cc2d4066a429","entry":"is_commonword","repo":"ElementAI/picard","repo_kind":"official","path":"seq2seq/utils/bridge_content_encoder.py","file_url":"https://github.com/ElementAI/picard/blob/HEAD/seq2seq/utils/bridge_content_encoder.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b724cc2d4066a429"}},{"code_sha256_prefix":"f39fdc1ce6cffe08","entry":"is_number","repo":"ElementAI/picard","repo_kind":"official","path":"seq2seq/utils/bridge_content_encoder.py","file_url":"https://github.com/ElementAI/picard/blob/HEAD/seq2seq/utils/bridge_content_encoder.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f39fdc1ce6cffe08"}},{"code_sha256_prefix":"d56a1f9221823a48","entry":"is_stopword","repo":"ElementAI/picard","repo_kind":"official","path":"seq2seq/utils/bridge_content_encoder.py","file_url":"https://github.com/ElementAI/picard/blob/HEAD/seq2seq/utils/bridge_content_encoder.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d56a1f9221823a48"}},{"code_sha256_prefix":"448eab4c7249a72c","entry":"normalize","repo":"ElementAI/picard","repo_kind":"official","path":"seq2seq/utils/dataset.py","file_url":"https://github.com/ElementAI/picard/blob/HEAD/seq2seq/utils/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"448eab4c7249a72c"}},{"code_sha256_prefix":"96f7360bd80c6f00","entry":"cosql_get_input","repo":"ElementAI/picard","repo_kind":"official","path":"seq2seq/utils/cosql.py","file_url":"https://github.com/ElementAI/picard/blob/HEAD/seq2seq/utils/cosql.py","link_basis":"first_harvest_node","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":"96f7360bd80c6f00"}},{"code_sha256_prefix":"d3c1fa9d710cc4ff","entry":"prepare_splits","repo":"servicenow/picard","repo_kind":"listed","path":"seq2seq/utils/dataset.py","file_url":"https://github.com/servicenow/picard/blob/HEAD/seq2seq/utils/dataset.py","link_basis":"plan_row","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":"d3c1fa9d710cc4ff"}},{"code_sha256_prefix":"b83f0da29c886b71","entry":"spider_get_input","repo":"ElementAI/picard","repo_kind":"official","path":"seq2seq/utils/spider.py","file_url":"https://github.com/ElementAI/picard/blob/HEAD/seq2seq/utils/spider.py","link_basis":"first_harvest_node","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":"b83f0da29c886b71"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}