A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification

TL;DR

This paper introduces a human-rated word complexity lexicon and a neural readability ranking model that outperforms existing systems in lexical simplification, also producing a large paraphrase resource.

Contribution

The paper presents a new human-rated lexicon and a neural model with Gaussian features for improved lexical simplification and paraphrase generation.

Findings

Model outperforms state-of-the-art systems

Created a lexicon of 15,000 words with human ratings

Produced SimplePPDB++, a large paraphrase resource

Abstract

Current lexical simplification approaches rely heavily on heuristics and corpus level features that do not always align with human judgment. We create a human-rated word-complexity lexicon of 15,000 English words and propose a novel neural readability ranking model with a Gaussian-based feature vectorization layer that utilizes these human ratings to measure the complexity of any given word or phrase. Our model performs better than the state-of-the-art systems for different lexical simplification tasks and evaluation datasets. Additionally, we also produce SimplePPDB++, a lexical resource of over 10 million simplifying paraphrase rules, by applying our model to the Paraphrase Database (PPDB).