Large-scale Semantic Parsing without Question-Answer                     Pairs

Reddy, Siva; Lapata, Mirella; Steedman, Mark

doi:10.1162/tacl_a_00190

Cited by 200 publications

(178 citation statements)

References 14 publications

Supporting

Mentioning

178

Contrasting

Order By: Relevance

“…These datasets include ATIS (Price, 1990;Dahl et al, 1994), Geo-Query (Zelle and Mooney, 1996), and JOBS (Tang and Mooney, 2001a). They have been studied extensively (Zelle and Mooney, 1996;Zettlemoyer and Collins, 2005;Wong and Mooney, 2007;Das et al, 2010;Liang et al, 2011;Banarescu et al, 2013;Artzi and Zettlemoyer, 2013;Reddy et al, 2014;Berant and Liang, 2014;Dong and Lapata, 2016). However, they are domain specific and there is no standard label guidance for multiple SQL queries.…”

Section: Related Work and Existing Datasetsmentioning

confidence: 99%

Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task

Zhang²,

Yang

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

559

593

View full text Add to dashboard Cite

We present Spider, a large-scale, complex and cross-domain semantic parsing and textto-SQL dataset annotated by 11 college students. It consists of 10,181 questions and 5,693 unique complex SQL queries on 200 databases with multiple tables, covering 138 different domains. We define a new complex and cross-domain semantic parsing and textto-SQL task where different complex SQL queries and databases appear in train and test sets. In this way, the task requires the model to generalize well to both new SQL queries and new database schemas. Spider is distinct from most of the previous semantic parsing tasks because they all use a single database and the exact same programs in the train set and the test set. We experiment with various state-of-the-art models and the best model achieves only 12.4% exact matching accuracy on a database split setting. This shows that Spider presents a strong challenge for future research. Our dataset and task are publicly available at https://yale-lily. github.io/spider.

show abstract

Section: Related Work and Existing Datasetsmentioning

confidence: 99%

Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task

Zhang²,

Yang

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

559

593

View full text Add to dashboard Cite

show abstract

“…Semantic parsing maps natural language to formal meaning representations. There are a range of representations, such as logic forms and executable programs (Zelle and Mooney, 1996;Zettlemoyer and Collins, 2005;Wong and Mooney, 2007;Das et al, 2010;Liang et al, 2011;Banarescu et al, 2013;Artzi and Zettlemoyer, 2013;Reddy et al, 2014;Berant and Liang, 2014;Pasupat and Liang, 2015;Herzig and Berant, 2018). As a sub-task of semantic parsing, the text-to-SQL problem has been studied for decades (Warren and Pereira, 1982;Popescu et al, 2003aPopescu et al, , 2004Li et al, 2006;Giordani and Moschitti, 2012;Wang et al, 2017b).…”

Section: Related Workmentioning

confidence: 99%

SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task

Yasunaga

Yang

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

164

145

View full text Add to dashboard Cite

Most existing studies in text-to-SQL tasks do not require generating complex SQL queries with multiple clauses or sub-queries, and generalizing to new, unseen databases. In this paper we propose SyntaxSQLNet, a syntax tree network to address the complex and crossdomain text-to-SQL generation task. Syn-taxSQLNet employs a SQL specific syntax tree-based decoder with SQL generation path history and table-aware column attention encoders. We evaluate SyntaxSQLNet on the Spider text-to-SQL task, which contains databases with multiple tables and complex SQL queries with multiple SQL clauses and nested queries. We use a database split setting where databases in the test set are unseen during training. Experimental results show that SyntaxSQLNet can handle a significantly greater number of complex SQL examples than prior work, outperforming the previous state-of-the-art model by 7.3% in exact matching accuracy. We also show that SyntaxSQLNet can further improve the performance by an additional 7.5% using a crossdomain augmentation method, resulting in a 14.8% improvement in total. To our knowledge, we are the first to study this complex and cross-domain text-to-SQL task. 1

show abstract

“…Neural semantic parsing based approach (Jia and Liang, 2016;Reddy et al, 2014;Dong and Lapata, 2016;Dong and Lapata, 2018;Guo et al, 2018) is gaining rising attention for knowledge-based question answer (KB-QA) in recent years since it does not rely on handcrafted features and is easy to adapt across domains. Traditional approaches usually retrieve answers from a small KB (e.g., small table) (Jia and Liang, 2016;Xiao et al, 2016) and are difficult to handle large-scale KBs.…”

Section: Introductionmentioning

confidence: 99%

Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base

Shen¹,

Geng²,

Qin³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

101

View full text Add to dashboard Cite

We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task into several subtasks and then solve them sequentially, which leads to following issues: 1) errors in earlier subtasks will be propagated and negatively affect downstream ones; and 2) each subtask cannot naturally share supervision signals with others. To tackle these issues, we propose an innovative multi-task learning framework where a pointer-equipped semantic parsing model is designed to resolve coreference in conversations, and naturally empower joint learning with a novel type-aware entity detection model. The proposed framework thus enables shared supervisions and alleviates the effect of error propagation. Experiments on a large-scale conversational question answering dataset containing 1.6M question answering pairs over 12.8M entities show that the proposed framework improves overall F1 score from 67% to 79% compared with previous state-of-the-art work.

show abstract

Large-scale Semantic Parsing without Question-Answer Pairs

Cited by 200 publications

References 14 publications

Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task

Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task

SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task

Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base

Contact Info

Product

Resources

About