Background Knowledge Injection for Interpretable Sequence Classification
|Title:||Background Knowledge Injection for Interpretable Sequence Classification||Authors:||Gsponer, Severin; Costabello, Luca; Van, Chan Le; Ifrim, Georgiana; et al.||Permanent link:||http://hdl.handle.net/10197/12037||Date:||16-Sep-2019||Online since:||2021-03-11T16:17:03Z||Abstract:||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.||Funding Details:||Science Foundation Ireland||Type of material:||Conference Publication||Keywords:||Sequence classification; Semantic embeddings; Clustering techniques||Other versions:||http://www.di.uniba.it/~loglisci/NFMCP2019/program.html||Language:||en||Status of Item:||Peer reviewed||Conference Details:||The 8th International New Frontiers in Mining Complex Patterns Workshop 2019, Wùzburg, Germany, 16 September 2019||This item is made available under a Creative Commons License:||https://creativecommons.org/licenses/by-nc-nd/3.0/ie/|
|Appears in Collections:||Computer Science Research Collection|
Insight Research Collection
Show full item record
If you are a publisher or author and have copyright concerns for any item, please email email@example.com and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.