Revisiting the Binary Linearization Technique for Surface Realization

Abstract

End-to-end neural approaches have achieved state-of-the-art performance in many natural language processing (NLP) tasks. Yet, they often lack transparency of the underlying decision-making process, hindering error analysis and certain model improvements. In this work, we revisit the binary linearization approach to surface realization, which exhibits more interpretable behavior, but was falling short in terms of prediction accuracy. We show how enriching the training data to better capture word order constraints almost doubles the performance of the system. We further demonstrate that encoding both local and global prediction contexts yields another considerable performance boost. With the proposed modifications, the system which ranked low in the latest shared task on multilingual surface realization now achieves best results in five out of ten languages, while being on par with the state-of-the-art approaches in others. 1

An Error Analysis Framework for Shallow Surface Realization

“…King and White (2018) drew attention to their model performance for non-projective sentences. Puzikov et al (2019) assessed their binary classifier for word ordering using the accuracy of predicting the position of a dependent with respect to its head, and a sibling. Yu et al (2019) showed that, for their system, error rates correlate with word order freedom, and reported linearization error rates for some frequent dependency types.…”