DeepAI AI Chat
Log In Sign Up

Background Knowledge Injection for Interpretable Sequence Classification

by   Severin Gsponer, et al.
Insight Centre for Data Analytics

Sequence classification is the supervised learning task of building models that predict class labels of unseen sequences of symbols. Although accuracy is paramount, in certain scenarios interpretability is a must. Unfortunately, such trade-off is often hard to achieve since we lack human-independent interpretability metrics. We introduce a novel sequence learning algorithm, that combines (i) linear classifiers - which are known to strike a good balance between predictive power and interpretability, and (ii) background knowledge embeddings. We extend the classic subsequence feature space with groups of symbols which are generated by background knowledge injected via word or graph embeddings, and use this new feature space to learn a linear classifier. We also present a new measure to evaluate the interpretability of a set of symbolic features based on the symbol embeddings. Experiments on human activity recognition from wearables and amino acid sequence classification show that our classification approach preserves predictive power, while delivering more interpretable models.


page 1

page 2

page 3

page 4


Interpretable Multiple-Kernel Prototype Learning for Discriminative Representation and Feature Selection

Prototype-based methods are of the particular interest for domain specia...

Learning to Decipher Hate Symbols

Existing computational models to understand hate speech typically frame ...

GapTV: Accurate and Interpretable Low-Dimensional Regression and Classification

We consider the problem of estimating a regression function in the commo...

Learning and Evaluating Sparse Interpretable Sentence Embeddings

Previous research on word embeddings has shown that sparse representatio...

Learning Maximally Predictive Prototypes in Multiple Instance Learning

In this work, we propose a simple model that provides permutation invari...

Incorporation of Human Knowledge into Data Embeddings to Improve Pattern Significance and Interpretability

Embedding is a common technique for analyzing multi-dimensional data. Ho...