Using Semantic Unification to Generate Regular Expressions from Natural Language
Name
Barzilay_Using Semantic.pdf
Size
304.29 KB
Format
Adobe PDF
Checksum (MD5)
90674a8a9112d737e4f70fec33a750e1
Author(s)
Kushman, Nate
Barzilay, Regina
Date Issued
June 2013
Journal
Proceedsings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Publisher
North American Chapter of the Association for Computational Linguistics (NAACL)
Citation
Kushman, Nate; Barzilay, Regina. "Using Semantic Unification to Generate Regular Expressions from Natural Language". North American Chapter of the Association for Computational Linguistics (NAACL) 2013.
Version
Author's final manuscript
Abstract
We consider the problem of translating natural language text queries into regular expressions which represent their meaning. The mismatch in the level of abstraction between the natural language representation and the regular expression representation make this a novel and challenging problem. However, a given regular expression can be written in many semantically equivalent forms, and we exploit this flexibility to facilitate translation by finding a form which more directly corresponds to the natural language. We evaluate our technique on a set of natural language queries and their associated regular expressions which we gathered from Amazon Mechanical Turk. Our model substantially outperforms a state-of-the-art semantic parsing baseline, yielding a 29% absolute improvement in accuracy.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike 3.0
Persistent DSpace Link
DOI of Published Version
http://naacl2013.naacl.org/abstracts/307.aspx
