Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge
Paper summary #### Introduction * Task of translating natural language queries into regular expressions without using domain specific knowledge. * Proposes a methodology for collecting a large corpus of regular expressions to natural language pairs. * Reports performance gain of 19.6% over state-of-the-art models. * [Link to the paper](http://arxiv.org/abs/1608.03000v1) #### Architecture * LSTM based sequence to sequence neural network (with attention) * Six layers * One-word embedding layer * Two encoder layers * Two decoder layers * One dense output layer. * Attention over encoder layer. * Dropout with the probability of 0.25. * 20 epochs, minibatch size of 32 and learning rate of 1 (with decay rate of 0.5) #### Dataset Generation * Created a public dataset - **NL-RX** - with 10K pair of (regular expression, natural language) * Two step generate-and-paraphrase approach * Generate step * Use handcrafted grammar to translate regular expressions to natural language. * Paraphrase step * Crowdsourcing the task of translating the rigid descriptions into more natural expressions. #### Results * Evaluation Metric * Functional equality check (called DFA-Equal) as same regular expression could be written in many ways. * Proposed architecture outperforms both the baselines - Nearest Neighbor classifier using Bag of Words (BoWNN) and Semantic-Unify
arxiv.org
arxiv-sanity.com
scholar.google.com
Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge
Nicholas Locascio and Karthik Narasimhan and Eduardo DeLeon and Nate Kushman and Regina Barzilay
arXiv e-Print archive - 2016 via arXiv
Keywords: cs.CL, cs.AI

more

Loading...
Your comment:


Short Science allows researchers to publish paper summaries that are voted on and ranked!
About