tax2vec: Constructing Interpretable Features from Taxonomies for Short Text Classification
This work addresses the challenge of leveraging background knowledge for short text classification, which is incremental as it builds on existing taxonomy-based methods.
The paper tackles the problem of short text classification by constructing interpretable semantic features from taxonomies, achieving comparable results to strong baselines like hierarchical attention neural networks and improving performance in data-scarce few-shot learning settings.
The use of background knowledge is largely unexploited in text classification tasks. This paper explores word taxonomies as means for constructing new semantic features, which may improve the performance and robustness of the learned classifiers. We propose tax2vec, a parallel algorithm for constructing taxonomy-based features, and demonstrate its use on six short text classification problems: prediction of gender, personality type, age, news topics, drug side effects and drug effectiveness. The constructed semantic features, in combination with fast linear classifiers, tested against strong baselines such as hierarchical attention neural networks, achieves comparable classification results on short text documents. The algorithm's performance is also tested in a few-shot learning setting, indicating that the inclusion of semantic features can improve the performance in data-scarce situations. The tax2vec capability to extract corpus-specific semantic keywords is also demonstrated. Finally, we investigate the semantic space of potential features, where we observe a similarity with the well known Zipf's law.