Unanimous Prediction for 100\% Precision with Application to Learning Semantic Mappings
Name
1606.06368.pdf
Description
Submitted version
Size
354.02 KB
Format
Adobe PDF
Checksum (MD5)
e84528e964bc4b5aaf5056925ea64c6e
Author(s)
Khani, Fereshte
Rinard, Martin
Liang, Percy
Date Issued
2016
Publisher
Association for Computational Linguistics
Citation
Khani, Fereshte, Rinard, Martin and Liang, Percy. 2016. "Unanimous Prediction for 100\% Precision with Application to Learning Semantic Mappings."
Version
Original manuscript
Abstract
© 2016 Association for Computational Linguistics. Can we train a system that, on any new input, either says "don't know" or makes a prediction that is guaranteed to be correct? We answer the question in the affirmative provided our model family is wellspecified. Specifically, we introduce the unanimity principle: only predict when all models consistent with the training data predict the same output. We operationalize this principle for semantic parsing, the task of mapping utterances to logical forms. We develop a simple, efficient method that reasons over the infinite set of all consistent models by only checking two of the models. We prove that our method obtains 100% precision even with a modest amount of training data from a possibly adversarial distribution. Empirically, we demonstrate the effectiveness of our approach on the standard GeoQuery dataset.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.18653/v1/p16-1090
