Integrating Transformer and Paraphrase Rules for Sentence Simplification

Sentence simplification aims to reduce the complexity of a sentence while retaining its original meaning. Current models for sentence simplification adopted ideas from ma- chine translation studies and implicitly learned simplification mapping rules from normal- simple sentence pairs. In this paper, we explore a novel model based on a multi-layer and multi-head attention architecture and we pro- pose two innovative approaches to integrate the Simple PPDB (A Paraphrase Database for Simplification), an external paraphrase knowledge base for simplification that covers a wide range of real-world simplification rules. The experiments show that the integration provides two major benefits: (1) the integrated model outperforms multiple state- of-the-art baseline models for sentence simplification in the literature (2) through analysis of the rule utilization, the model seeks to select more accurate simplification rules. The code and models used in the paper are available at https://github.com/ Sanqiang/text_simplification.

PDF Abstract EMNLP 2018 PDF EMNLP 2018 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Text Simplification ASSET DMASS-DCSS SARI (EASSE>=0.2.1) 38.67 # 7
BLEU 71.44* # 3
Text Simplification Newsela DMASS + DCSS SARI 27.28 # 9
Text Simplification TurkCorpus DMASS-DCSS SARI (EASSE>=0.2.1) 40.45 # 7

Methods


No methods listed for this paper. Add relevant methods here