SIERA: An Evaluation Metric for Text Simplification using the Ranking Model and Data Augmentation by Edit Operations

Abstract

Automatic evaluation metrics are indispensable for text simplification (TS) research. The past TS research adopts three evaluation aspects: fluency, meaning preservation and simplicity. However, there is little consensus on a metric to measure simplicity, a unique aspect of TS compared with other text generation tasks. In addition, many of the existing metrics require reference simplified texts for evaluation. Thus, the cost of collecting reference texts is also an issue. This study proposes a new automatic evaluation metric, SIERA, for sentence simplification. SIERA employs a ranking model for the order relation of simplicity, which is trained by pairs of the original and simplified sentences. It does not require reference sentences for either training or evaluation. The sentence pairs for training are further augmented by the proposed method that utlizes edit operations to generate intermediate sentences with the simplicity between the original and simplified sentences. Using three evaluation datasets for text simplification, we compare SIERA with other metrics by calculating the correlations between metric values and human ratings. The results showed SIERA’s superiority over other metrics with a reservation that the quality of evaluation sentences is consistent with that of the training data.

Resources

Details