Grounded Adaptation for Zero-shot Executable Semantic Parsing

Zhong, Victor; Lewis, Mike; Wang, Sida I.; Zettlemoyer, Luke

doi:10.18653/v1/2020.emnlp-main.558

Cited by 60 publications

(53 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Base Parser + BERT-base 66.8 63.3 Base Parser + BERT-base + DG-MAML 68.9 65.2 With BERT-large: RYANSQL + BERT-large (Choi et al, 2020) 70.6 60.6 RAT-SQL + BERT-large 69.7 65.6 Execution Accuracy GAZP + Distil-BERT (Zhong et al, 2020) 59.…”

Section: Our Modelsmentioning

confidence: 99%

Meta-Learning for Domain Generalization in Semantic Parsing

Wang¹,

Lapata²,

Titov³

2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

The importance of building semantic parsers which can be applied to new domains and generate programs unseen at training has long been acknowledged, and datasets testing outof-domain performance are becoming increasingly available. However, little or no attention has been devoted to learning algorithms or objectives which promote domain generalization, with virtually all existing approaches relying on standard supervised learning. In this work, we use a meta-learning framework which targets zero-shot domain generalization for semantic parsing. We apply a modelagnostic training algorithm that simulates zeroshot parsing by constructing virtual train and test sets from disjoint domains. The learning objective capitalizes on the intuition that gradient steps that improve source-domain performance should also improve target-domain performance, thus encouraging a parser to generalize to unseen target domains. Experimental results on the (English) Spider and Chinese Spider datasets show that the meta-learning objective significantly boosts the performance of a baseline parser.

show abstract

Section: Our Modelsmentioning

confidence: 99%

Meta-Learning for Domain Generalization in Semantic Parsing

Wang¹,

Lapata²,

Titov³

2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…EditSQL , IGSQL (Cai and Wan, 2020) and R 2 SQL (Hui et al) consider the dialogue context during translating the utterance into SQL query. GAZP (Zhong et al, 2020) proposes a zero-shot method to adapt an existing semantic parser to new domains. PIIA proposes a human-in-loop method to enhance Textto-SQL performance.…”

Section: Related Workmentioning

confidence: 99%

ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser

Chen¹,

Lu²,

Zhao³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Given a database schema, Text-to-SQL aims to translate a natural language question into the corresponding SQL query. Under the setup of cross-domain, traditional semantic parsing models struggle to adapt to unseen database schemas. To improve the model generalization capability for rare and unseen schemas, we propose a new architecture, ShadowGNN, which processes schemas at abstract and semantic levels. By ignoring names of semantic items in databases, abstract schemas are exploited in a well-designed graph projection neural network to obtain delexicalized representation of question and schema. Based on the domain-independent representations, a relation-aware transformer is utilized to further extract logical linking between question and schema. Finally, a SQL decoder with context-free grammar is applied. On the challenging Text-to-SQL benchmark Spider, empirical results show that ShadowGNN outperforms state-of-the-art models. When the annotated data is extremely limited (only 10% training set), ShadowGNN gets over absolute 5% performance gain, which shows its powerful generalization ability. Our implementation will be open-sourced at https://github. com/WowCZ/shadowgnn.

show abstract

“…Open Domain Question Answering ODQA has been extensively studied recently including extractive models (Chen et al, 2017;Clark and Gardner, 2018;Wang et al, 2019;Min et al, 2019;Yang et al, 2019) that predict spans from evidence passages, and generative models Lewis et al, 2020;Izacard and Grave, 2020) that directly generate the answers. Wang et al (2018b,c); Nogueira and Cho (2019) proposed to rerank the retrieved passages to get higher top-n recall.…”

Section: Related Workmentioning

confidence: 99%

“…Wang et al (2018b,c); Nogueira and Cho (2019) proposed to rerank the retrieved passages to get higher top-n recall. (Zhong et al, 2017), Spider and CoSQL being introduced, many works have shown promising progress on these dataset He et al, 2019;Hwang et al, 2019;Min et al, 2019;Choi et al, 2020;Lyu et al, 2020;Zhong et al, 2020;Shi et al, 2020). Another line of work proposes to reason over tables without generating logical forms (Neelakantan et al, 2015;Lu et al, 2016;Herzig et al, 2020;Yin et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

“…Open-domain question answering (ODQA) is a task to answer factoid questions without a prespecified domain. Recently, generative models Lewis et al, 2020;Izacard and Grave, 2020) have achieved the state-of-the-art performance on many ODQA tasks. These approaches all share the common pipeline where the first stage is retrieving evidence from the free-form text in Wikipedia.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering

Li¹,

Ng²,

Xu³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

The current state-of-the-art generative models for open-domain question answering (ODQA) have focused on generating direct answers from unstructured textual information. However, a large amount of world's knowledge is stored in structured databases, and need to be accessed using query languages such as SQL. Furthermore, query languages can answer questions that require complex reasoning, as well as offering full explainability. In this paper, we propose a hybrid framework that takes both textual and tabular evidence as input and generates either direct answers or SQL queries depending on which form could better answer the question. The generated SQL queries can then be executed on the associated databases to obtain the final answers. To the best of our knowledge, this is the first paper that applies Text2SQL to ODQA tasks. Empirically, we demonstrate that on several ODQA datasets, the hybrid methods consistently outperforms the baseline models that only take homogeneous input by a large margin. Specifically we achieve state-of-theart performance on OpenSQuAD dataset using a T5-base model. In a detailed analysis, we demonstrate that the being able to generate structural SQL queries can always bring gains, especially for those questions that requires complex reasoning.

show abstract

Grounded Adaptation for Zero-shot Executable Semantic Parsing

Cited by 60 publications

References 14 publications

Meta-Learning for Domain Generalization in Semantic Parsing

Meta-Learning for Domain Generalization in Semantic Parsing

ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser

Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering

Contact Info

Product

Resources

About