EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
This addresses the problem of generating simpler sentences for applications like accessibility or readability, offering a novel method that mimics human editing processes.
The paper tackles sentence simplification by introducing a model that learns explicit edit operations (ADD, DELETE, KEEP) using a neural programmer-interpreter approach, outperforming previous state-of-the-art models with SARI score improvements of +0.95, +1.89, and +1.41 on three benchmark corpora.
We present the first sentence simplification model that learns explicit edit operations (ADD, DELETE, and KEEP) via a neural programmer-interpreter approach. Most current neural sentence simplification systems are variants of sequence-to-sequence models adopted from machine translation. These methods learn to simplify sentences as a byproduct of the fact that they are trained on complex-simple sentence pairs. By contrast, our neural programmer-interpreter is directly trained to predict explicit edit operations on targeted parts of the input sentence, resembling the way that humans might perform simplification and revision. Our model outperforms previous state-of-the-art neural sentence simplification models (without external knowledge) by large margins on three benchmark text simplification corpora in terms of SARI (+0.95 WikiLarge, +1.89 WikiSmall, +1.41 Newsela), and is judged by humans to produce overall better and simpler output sentences.