Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge
arXiv e-Print archive - 2016 via Local arXiv
First published: 2016/08/09 (4 years ago) Abstract: 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.
* 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)
* 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.
* 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