2016/06/24 by Camille Jandot, Patrice Y. Simard, Jandot, Camille +8 · 1 citation
Computer Science · Mathematics · #Natural Language Processing Techniques #Sentiment Analysis and Opinion Mining #Topic Modeling #cs.CL #stat.ML
paper · pdf · doi:10.48550/arxiv.1606.07545
presented at 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016), New York, NY
arxiv created 2016/06/24 · arxiv updated 2016/06/27
In text classification, dictionaries can be used to define human-comprehensible features. We propose an improvement to dictionary features called smoothed dictionary features. These features recognize document contexts instead of n-grams. We describe a principled methodology to solicit dictionary features from a teacher, and present results showing that models built using these human-comprehensible features are competitive with models trained with Bag of Words features.