(Psycho-)Linguistic Features Meet Transformer Models for Improved Explainable and Controllable Text Simplification

TL;DR

This paper enhances text simplification by integrating psycho-linguistic features with transformer models to improve explainability and controllability, enabling tailored simplifications for different user needs.

Contribution

It introduces a method combining linguistic features with pre-trained models for better complexity prediction and extends a Seq2Seq model for explicit attribute control.

Findings

Improved explainable complexity prediction accuracy.

Enhanced controllability of text simplification with attribute conditioning.

Significant performance gains in both within-domain and out-of-domain tests.

Abstract

State-of-the-art text simplification (TS) systems adopt end-to-end neural network models to directly generate the simplified version of the input text, and usually function as a blackbox. Moreover, TS is usually treated as an all-purpose generic task under the assumption of homogeneity, where the same simplification is suitable for all. In recent years, however, there has been increasing recognition of the need to adapt the simplification techniques to the specific needs of different target groups. In this work, we aim to advance current research on explainable and controllable TS in two ways: First, building on recently proposed work to increase the transparency of TS systems, we use a large set of (psycho-)linguistic features in combination with pre-trained language models to improve explainable complexity prediction. Second, based on the results of this preliminary task, we extend a state-of-the-art Seq2Seq TS model, ACCESS, to enable explicit control of ten attributes. The results of experiments show (1) that our approach improves the performance of state-of-the-art models for predicting explainable complexity and (2) that explicitly conditioning the Seq2Seq model on ten attributes leads to a significant improvement in performance in both within-domain and out-of-domain settings.