FR: Folded Rationalization with a Unified Encoder
This addresses a specific challenge in interpretable machine learning for text analysis, offering a novel solution to improve model performance and reliability.
The paper tackles the degeneration problem in two-phase rationalization models, where the predictor overfits to noise from an untrained generator, by proposing Folded Rationalization (FR) that folds the two phases into one using a unified encoder, resulting in up to a 10.3% improvement in F1 score over state-of-the-art methods.
Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected pieces. However, such a two-phase model may incur the degeneration problem where the predictor overfits to the noise generated by a not yet well-trained generator and in turn, leads the generator to converge to a sub-optimal model that tends to select senseless pieces. To tackle this challenge, we propose Folded Rationalization (FR) that folds the two phases of the rationale model into one from the perspective of text semantic extraction. The key idea of FR is to employ a unified encoder between the generator and predictor, based on which FR can facilitate a better predictor by access to valuable information blocked by the generator in the traditional two-phase model and thus bring a better generator. Empirically, we show that FR improves the F1 score by up to 10.3% as compared to state-of-the-art methods.