Learning How to Simplify From Explicit Labeling of Complex-Simplified Text Pairs

Current research in text simplification has been hampered by two central problems: (i) the small amount of high-quality parallel simplification data available, and (ii) the lack of explicit annotations of simplification operations, such as deletions or substitutions, on existing data. While the recently introduced Newsela corpus has alleviated the first problem, simplifications still need to be learned directly from parallel text using black-box, end-to-end approaches rather than from explicit annotations. These complex-simple parallel sentence pairs often differ to such a high degree that generalization becomes difficult. End-to-end models also make it hard to interpret what is actually learned from data. We propose a method that decomposes the task of TS into its sub-problems. We devise a way to automatically identify operations in a parallel corpus and introduce a sequence-labeling approach based on these annotations. Finally, we provide insights on the types of transformations that different approaches can model.

PDF Abstract IJCNLP 2017 PDF IJCNLP 2017 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Text Simplification Newsela SeqLabel SARI 29.53* # 11
Text Simplification PWKP / WikiSmall SeqLabel SARI 30.50* # 8
Text Simplification TurkCorpus SeqLabel SARI (EASSE>=0.2.1) 37.08* # 22