--- title: "SEQZERO — paper by Yang et al. (2022) — summary and ideas" description: "The paper tackles semantic parsing (mapping questions to formal queries such as SQL) when only a… 1 reference, cited by 23 papers here." authors: ["Jingfeng Yang", "Haoming Jiang", "Qingyu Yin", "Danqing Zhang", "Bing Yin", "Diyi Yang"] year: 2022 venue: "Findings of the Association for Computational Linguistics: NAACL 2022" source: "https://aclanthology.org/2022.findings-naacl.5/" doi: "10.18653/v1/2022.findings-naacl.5" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/yang-2022-seqzero-few-shot-compositional-semantic/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yang-2022-seqzero-few-shot-compositional-semantic/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2022](https://md.research.elamur.ai/free/en/papers/2022/page/4/) / SEQZERO: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models # SEQZERO: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models **Authors:** [Jingfeng Yang](https://md.research.elamur.ai/free/en/authors/jingfeng-yang/), [Haoming Jiang](https://md.research.elamur.ai/free/en/authors/haoming-jiang/), [Qingyu Yin](https://md.research.elamur.ai/free/en/authors/qingyu-yin/), Danqing Zhang, [Bing Yin](https://md.research.elamur.ai/free/en/authors/bing-yin/) and [Diyi Yang](https://md.research.elamur.ai/free/en/authors/diyi-yang/) · **Year:** 2022 · **Venue:** [Findings of the Association for Computational Linguistics: NAACL 2022](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2022](https://md.research.elamur.ai/free/en/venues/findings/2022/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2022.findings-naacl.5/) · [PDF](https://aclanthology.org/2022.findings-naacl.5.pdf) · [DOI 10.18653/v1/2022.findings-naacl.5](https://doi.org/10.18653/v1/2022.findings-naacl.5) · [OpenAlex](https://openalex.org/W4280633590) **Citations:** 15 citations (OpenAlex, 2026-10-14) · [23](https://md.research.elamur.ai/free/en/papers/yang-2022-seqzero-few-shot-compositional-semantic/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary The paper tackles semantic parsing (mapping questions to formal queries such as SQL) when only a handful of annotated pairs exist. Earlier few-shot approaches fine-tune pretrained LMs to produce a canonical utterance that a grammar then converts into the query. Because these utterances are long and compositional, they need a lot of training data. Small fine-tuning sets also cause overfitting to spurious patterns and poor compositional out-of-distribution generalization. SEQZERO breaks a query into its sub-clauses (FROM, SELECT, WHERE and so on) and predicts them one at a time. Each step fills a short slot in a natural-language prompt, with earlier clauses supplied as context. Every slot is scored by two models: - a fine-tuned BART; - an untuned (zero-shot) BART restricted to a set of candidate values. The zero-shot model assigns very little probability to those candidates, so the authors rescale its constrained probabilities before a linear ensemble. On the compositional splits of GeoQuery and the newly released EcommerceQuery, the method reaches state-of-the-art results among BART-based parsers. This suggests that combining zero-shot and few-shot models can reduce bias-driven errors. ## Key points - Directly fine-tuned BART on GeoQuery tends to latch onto spurious cues, for example predicting the wrong table for familiar question patterns. The authors attribute about 75% of the Base model's test errors to this kind of compositional OOD mistake. - The zero-shot model's candidate values come from: - SQL grammar; - table schema; - the input utterance; - training data. A trie (prefix tree) determines which tokens are allowed at each decoding step. - Constrained probability rescaling is what lets the zero-shot model actually contribute to the ensemble. Weight-space ensembling in the style of Wortsman et al. (2021) did not work in this generation setting. - The paper contributes a new E-commerce product-search dataset, EcommerceQuery. Code and data are announced at github.com/amzn/SeqZero. - The work was published in Findings of NAACL 2022 by authors from Amazon and Georgia Tech. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Georgia Institute of Technology](https://md.research.elamur.ai/free/en/universities/georgia-institute-of-technology/) — University, Atlanta, United States · 133 works · 24,497 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works 🧭 Topics (1): [🧾 Semantic parsing & meaning representation](https://md.research.elamur.ai/free/en/topics/semantic-parsing/) · 185 works ## Cite Cite as: Jingfeng Yang, Haoming Jiang, Qingyu Yin, Danqing Zhang, Bing Yin and Diyi Yang. 2022. SEQZERO: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models. Findings of the Association for Computational Linguistics: NAACL 2022. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{yang2022seqzero, title = {{SEQZERO: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models}}, author = {Jingfeng Yang, Haoming Jiang, Qingyu Yin, Danqing Zhang, Bing Yin and Diyi Yang}, booktitle = {Findings of the Association for Computational Linguistics: NAACL 2022}, year = {2022}, doi = {10.18653/v1/2022.findings-naacl.5}, url = {https://doi.org/10.18653/v1/2022.findings-naacl.5} } ``` - [← previous ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding](https://md.research.elamur.ai/free/en/papers/peng-2022-ernie-layout-layout-knowledge/) - [next → Should We Ban English NLP for a Year?](https://md.research.elamur.ai/free/en/papers/sogaard-2022-should-we-ban-english-nlp/) - [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/page/4/) ## References 1 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Ekin Akyürek, Afra Feyza Akyürek, and Jacob Andreas. 2020. Learning to recombine and resample data for compositional generalization. arXiv preprint arXiv:2010.03706. \#\# Conclusion — [arXiv:2010.03706](https://arxiv.org/abs/2010.03706) [find](https://scholar.google.com/scholar?q=Ekin+Aky%C3%BCrek%2C+Afra+Feyza+Aky%C3%BCrek%2C+and+Jacob+Andreas%2E+2020%2E+Learning+to+recombine+and+resample+data+for+compositional+generalization%2E+arXiv+preprint+arXiv%3A2010%2E03706%2E+%5C%23%5C%23+Conclusion+%E2%80%94+%5BarXiv%3A2010%2E0370) *Updated 30 October 2026*