Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge

By Nicholas Locascio, Karthik Narasimhan, Eduardo DeLeon, Nate Kushman, Regina Barzilay. 2016

95 citations recorded by the source corpus.

This paper explores the task of translating natural language queries into regular expressions which embody their meaning. In contrast to prior work, the proposed neural model does not utilize domain-specific crafting, learning to translate directly from a parallel corpus. To fully explore the potential of neural models, we propose a methodology for collecting a large corpus of regular expression, natural language pairs. Our resulting model achieves a performance gain of 19.6% over previous state-of-the-art models.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms (2019, background): “While recent works like (Liang et al., 2018; Locascio et al., 2016) have explored representing math word problems with logical formalisms and regular expressions, our work is the first to provide well-defined formalisms for representing intermediate problem-solving steps that are shown to be general”
Deep Neural Solver for Math Word Problems (2017, methodology): “Recently, the task of translating natural language queries into regular expressions is explored by using a seq2seq model Locascio et al. (2016), which achieves a performance gain of 19.6% over previous state-of-the-art models.”
Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow (2018, methodology): “ code summarization [2], automatic documentation of source code [44], deobfuscation [16, 34, 40], cross-language porting [27, 28], code retrieval [3, 42] and even code synthesis from natural language [7, 21, 32, 47]. Besides the creativity and diligence of the researchers involved, these recent succ”
Learning a Neural Semantic Parser from User Feedback (2017, methodology): “Although diverse meaning representation languages have been used with semantic parsers – such as regular expressions (Kushman and Barzi-lay, 2013; Locascio et al., 2016), Abstract Meaning Representations (AMR) (Artzi et al., 2015; Misra and Artzi, 2016), and systems of equations (Kushman et al.,…”
NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System (2018, background): “(Kushman and Barzilay, 2013; Locascio et al., 2016) formally verify the equivalence of different regular expressions by converting them to minimal deterministic ﬁnite automaton (DFAs).”
Neural Semantic Parsing with Type Constraints for Semi-Structured Tables (2017, methodology): “This approach is taken by recent neural semantic parsers (Jia and Liang, 2016; Dong and Lapata, 2016; Locascio et al., 2016; Ling et al., 2016).”
JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation (2019, background): “, 2013), regular expressions (Kushman and Barzilay, 2013; Locascio et al., 2016), database queries (Iyer et al.”
Retrieval-Based Neural Code Generation (2018, methodology): “Sequential approaches (Ling et al., 2016; Jia and Liang, 2016; Locascio et al., 2016) convert the target code into a sequence of symbols and apply a sequence-to-sequence model, but this approach does not ensure that the output will be syntactically correct.”
Program Synthesis from Natural Language Using Recurrent Neural Networks (2017, methodology): “[19] uses RNN encoder-decoder to synthesize regular expressions based on a natural language description.”