A Review of Parallel Corpora for Automatic Text Simplification. Key Challenges Moving Forward

This review of parallel corpora for automatic text simplification (ATS) involves an analysis of forty-nine papers wherein the corpora are presented, focusing on corpora in the Indo-European languages of Western Europe. We improve on recent corpora reviews by reporting on the target audience of the ATS, the language and domain of the source text, and other metadata for each corpus, such as alignment level, annotation strategy, and the transformation applied to the simplified text. The key findings of the review are: 1) the lack of resources that address ATS aimed at domains which are important for social inclusion, such as health and public administration; 2) the lack of resources aimed at audiences with mild cognitive impairment; 3) the scarcity of experiments where the target audience was directly involved in the development of the corpus; 4) more than half the proposals do not include any extra annotation, thereby lacking detail on how the simplification was done, or the linguistic phenomenon tackled by the simplification; 5) other types of annotation, such as the type and frequency of the transformation applied could identify the most frequent simplification strategies; and, 6) future strategies to advance the field of ATS could leverage automatic procedures to make the annotation process more agile and efficient.