Monolingual sentence matching for text simplification
This work addresses text simplification alignment, an incremental improvement for NLP applications.
The paper tackled monolingual sentence alignment for text simplification in Wikipedia by introducing a convolutional neural network trained semi-supervised, and showed that rescoring and adaptation improved performance over a knowledge-based method.
This work improves monolingual sentence alignment for text simplification, specifically for text in standard and simple Wikipedia. We introduce a convolutional neural network structure to model similarity between two sentences. Due to the limitation of available parallel corpora, the model is trained in a semi-supervised way, by using the output of a knowledge-based high performance aligning system. We apply the resulting similarity score to rescore the knowledge-based output, and adapt the model by a small hand-aligned dataset. Experiments show that both rescoring and adaptation improve the performance of knowledge-based method.