Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes

By Chris Quirk, Raymond J. Mooney, Michel Galley. 2015

164 citations recorded by the source corpus.

Using natural language to write programs is a touchstone problem for computational linguistics. We present an approach that learns to map natural-language descriptions of simple “if-then” rules to executable code. By training and testing on a large corpus of naturally-occurring programs (called “recipes”) and their natural language descriptions, we demonstrate the ability to effectively map language to code. We compare a number of semantic parsing approaches on the highly noisy training data collected from ordinary users, and find that loosely synchronous systems perform best.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

A Survey of Machine Learning for Big Code and Naturalness (2017, background): “This area has attracted growing interest, with applications such as converting natural language to Excel macros [77], Java expressions [82], shell commands [118, 119], simple if-then programs [161], regular expressions [110], and to SQL queries [200].”
Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems (2017, background): “…2013), and inherits ideas from the extensive literature on semantic parsing (Jones et al., 2012; Berant et al., 2013; Andreas et al., 2013; Quirk et al., 2015; Liang et al., 2016; Neelakantan et al., 2016) and program generation (Reed and de Fre-itas, 2016; Graves et al., 2016), namely,…”
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (2018, background): “Recently, researchers have constructed some datasets for code generation including IFTTT (Quirk et al., 2015), DJANGO (Oda et al., 2015), HEARTHSTONE (Ling et al., 2016), NL2Bash (Lin et al., 2018), and CoNaLa (Yin et al., 2018).”
Latent Predictor Networks for Code Generation (2016, methodology): “This dataset presents additional challenges to prior work in code generation (Wong and Mooney, 2006; Jones et al., 2012; Lei et al., 2013; Artzi et al., 2015; Quirk et al., 2015), including the handling of structured input—i.”
Language to Logical Form with Neural Attention (2016, methodology): “This may be due to the size of Quirk et al. (2015) and the way it was created – user curated descriptions are often of low quality, and thus align very loosely to their corresponding ASTs.”
A Parallel Corpus of Python Functions and Documentation Strings for Automated Code Documentation and Code Generation (2017, methodology): “Other corpora have been assembled from user-generated descriptions matched to code fragments mined from public websites such as StackOverﬂow 2 (Allamanis et al., 2015b; Iyer et al., 2016) or IFTTT 3 (Quirk et al., 2015).”
Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow (2018, background): “ line of mining intent-snippet pairs from SO (e.g., [15, 44, 46, 48]), while there has been research on miningfromotherdatasourcessuchasAPIdocumentation[5,6,24], code comments [43], specialized sites [32], parameter/method/class names [1, 37], and developer mailing lists [31]. It is likely that it c”
NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System (2018, background): “Extracting good alignments from them is very challenging (Quirk et al., 2015; Iyer et al., 2016; Yao et al., 2018).”
VirtualHome: Simulating Household Activities Via Programs (2018, background): “Given a sentence describing conditions, [17] produces If-This-Then-That code.”
SQLizer: query synthesis from natural language (2017, methodology): “…query synthesis, natural language has also been used as the preferred specification mechanism in the context of smartphone automation scripts [Le et al. 2013], “if-then-else recipes" [Quirk et al. 2015], spreadsheet programming [Gulwani and Marron 2014], and string manipulation [Raza et al. 2015].”
Program Synthesis from Natural Language Using Recurrent Neural Networks (2017, background): “Semantic parsing. problem of mapping natural language to programs or other formal representations has been extensively studied in the natural language processing community [1, 3, 6, 30, 37].”
From Textbooks to Knowledge: A Case Study in Harvesting Axiomatic Knowledge from Textbooks to Solve Geometry Problems (2017, unknown): “More speciﬁcally, Liu et al. (2016a) and Quirk et al. (2015) learn “If-Then” and “If-This-Then-That” rules, respectively.”
Studying the effect of AI Code Generators on Supporting Novice Learners in Introductory Programming (2023, unknown): “Various methods have been employed, such as using semantic parsers [4, 9, 11, 18, 33, 34, 47, 50, 51, 56, 68, 80] and machine learning [5, 54, 71–73, 93, 95].”
Building Natural Language Interfaces to Web APIs (2017, methodology): “For example, web services (e.g., weather, sports, and inance) hosted in the cloud provide data and services to end users via web APIs [1, 7], and IFTTT [19].”
Statistical learning for semantic parsing: A survey (2019, unknown): “Reference [91] created this dataset in 2015.”
Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing (2018, background): “…2016) 5 Related Work Semantic parsing has received signiﬁcant attention for a long time (Kate and Mooney, 2006; Clarke et al., 2010; Krishnamurthy and Mitchell, 2012; Artzi and Zettlemoyer, 2013; Berant and Liang, 2014; Quirk et al., 2015; Artzi et al., 2015; Reddy et al., 2017; Chen et al., 2018).”
Natural Language Interfaces with Fine-Grained User Interaction: A Case Study on Web APIs (2018, background): “With the growth of web services, IoT devices, and mobile apps, natural language interfaces to API (NL2API) have aracted signicant aention [7, 25, 27].”