LinguaSynth: Heterogeneous Linguistic Signals for News Classification
This addresses interpretability and efficiency issues for NLP practitioners, offering a competitive alternative to deep neural networks, though it is incremental as it builds on existing feature-based methods.
The paper tackled the problem of interpretability and computational efficiency in deep learning for NLP by proposing LinguaSynth, a framework integrating five linguistic feature types in a logistic regression model, achieving 84.89% accuracy on the 20 Newsgroups dataset and surpassing a TF-IDF baseline by 3.32%.
Deep learning has significantly advanced NLP, but its reliance on large black-box models introduces critical interpretability and computational efficiency concerns. This paper proposes LinguaSynth, a novel text classification framework that strategically integrates five complementary linguistic feature types: lexical, syntactic, entity-level, word-level semantics, and document-level semantics within a transparent logistic regression model. Unlike transformer-based architectures, LinguaSynth maintains interpretability and computational efficiency, achieving an accuracy of 84.89 percent on the 20 Newsgroups dataset and surpassing a robust TF-IDF baseline by 3.32 percent. Through rigorous feature interaction analysis, we show that syntactic and entity-level signals provide essential disambiguation and effectively complement distributional semantics. LinguaSynth sets a new benchmark for interpretable, resource-efficient NLP models and challenges the prevailing assumption that deep neural networks are necessary for high-performing text classification.