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

Fernando Alva-Manchego, Joachim Bingel, Gustavo Paetzold, Carolina Scarton, Lucia Specia


Abstract
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.
Anthology ID:
I17-1030
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
295–305
Language:
URL:
https://aclanthology.org/I17-1030
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/I17-1030.pdf
Note:
 I17-1030.Notes.pdf
Code
 ghpaetzold/massalign
Data
NewselaTurkCorpus