Data-Driven Sentence Simplification: Survey and Benchmark

Data-Driven Sentence Simplification: Survey and Benchmark Fernando Alva-Manchego University of Sheffield Department of Computer Science f.alva@sheffield.ac.uk Carolina Scarton University of Sheffield Department of Computer Science c.scarton@sheffield.ac.uk Lucia Specia Imperial College London Department of Computing l.specia@imperial.ac.uk Sentence Simplification (SS) aims to modify a sentence in order to make it easier to read and understand. In order to do so, several rewriting transformations can be performed such as replacement, reordering, and splitting. Executing these transformations while keeping sentences grammatical, preserving their main idea, and generating simpler output, is a challenging and still far from solved problem. In this article, we survey research on SS, focusing on approaches that attempt to learn how to simplify using corpora of aligned original-simplified sentence pairs in English, which is the dominant paradigm nowadays. We also include a benchmark of different approaches on common data sets so as to compare them and highlight their strengths and limitations. We expect that this survey will serve as a starting point for researchers interested in the task and help spark new ideas for future developments. 1. Introduction Text Simplification (TS) is the task of modifying the content and structure of a text in order to make it easier to read and understand, while retaining its main idea and ap- proximating its original meaning. A simplified version of a text could benefit users with several reading difficulties, such as non-native speakers (Paetzold 2016), people with aphasia (Carroll et al. 1998), dyslexia (Rello et al. 2013b), or autism (Evans, Orasan, and Dornescu 2014). Simplifying a text automatically could also help improve performance Submission received: 8 June 2018; revise d version received: 9 August 2019; accepted for publication: 15 September 2019. https://doi.org/10.1162/COLI a 00370 © 2020 Association for Computational Linguistics Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license Computational Linguistics Volume 46, Number 1 on other language processing tasks, such as parsing (Chandrasekar, Doran, and Srinivas 1996), summarization (Vanderwende et al. 2007; Silveira and Branco 2012), information extraction (Evans 2011), semantic role labeling (Vickrey and Koller 2008), and Machine Translation (MT) (Hasler et al. 2017). Most research on TS has focused on studying simplification of individual sentences. Reducing the scope of the problem has allowed the easier collection and curation of corpora, as well as adapting methods from other text generation tasks, mainly MT. It can be argued that “true” TS (i.e., document-level) cannot be achieved by simplifying sentences one at a time, and we make a call in Section 6 for the field to move in that direction. However, because the goal of this article is to review what has been done in TS so far, our survey is limited to Sentence Simplification (SS). When simplifying sentences, different rewriting transformations are performed, which range from replacing complex words or phrases for simpler synonyms, to chang- ing the syntactic structure of the sentence (e.g., splitting or reordering components). Modern SS approaches are data-driven; that is, they attempt to learn these transfor- mations using parallel corpora of aligned original-simplified sentences. …

Content truncated to 500 words