Feature-guided Neural Model Training for Supervised Document Representation Learning
Aili Shen, Bahar Salehi, Jianzhong Qi, Timothy Baldwin
Proceedings of the 17th Workshop of the Australasian Language Technology Association | Australasian Language Technology Association | Published : 2019
With the advent of neural models, there has been a rapid move away from feature engineering, or at best, simplistically combining handcrafted features with learned representations as side information. We propose a method that uses hand-crafted features to guide learning by explicitly attending to feature indicators when learning the relationship between the input and target variables. In experiments over two different tasks — quality assessment of Wikipedia articles and popularity prediction of online petitions— we demonstrate that the proposed method yields neural models that consistently outperform those that simply use hand-crafted features as side information.