Lexical simplification benchmarks for English, Portuguese, and Spanish

Abstract

Even in highly-developed countries, as many as 15–30% of the population can only understand texts written using a basic vocabulary. Their understanding of everyday texts is limited, which prevents them from taking an active role in society and making informed decisions regarding healthcare, legal representation, or democratic choice. Lexical simplification is a natural language processing task that aims to make text understandable to everyone by replacing complex vocabulary and expressions with simpler ones, while preserving the original meaning. It has attracted considerable attention in the last 20 years, and fully automatic lexical simplification systems have been proposed for various languages. The main obstacle for the progress of the field is the absence of high-quality datasets for building and evaluating lexical simplification systems. In this study, we present a new benchmark dataset for lexical simplification in English, Spanish, and (Brazilian) Portuguese, and provide details about data selection and annotation procedures, to enable compilation of comparable datasets in other languages and domains. As the first multilingual lexical simplification dataset, where instances in all three languages were selected and annotated using comparable procedures, this is the first dataset that offers a direct comparison of lexical simplification systems for three languages. To showcase the usability of the dataset, we adapt two state-of-the-art lexical simplification systems with differing architectures (neural vs. non-neural) to all three languages (English, Spanish, and Brazilian Portuguese) and evaluate their performances on our new dataset. For a fairer comparison, we use several evaluation measures which capture varied aspects of the systems' efficacy, and discuss their strengths and weaknesses. We find that a state-of-the-art neural lexical simplification system outperforms a state-of-the-art non-neural lexical simplification system in all three languages, according to all evaluation measures. More importantly, we find that the state-of-the-art neural lexical simplification systems perform significantly better for English than for Spanish and Portuguese, thus posing a question if such an architecture can be used for successful lexical simplification in other languages, especially the low-resourced ones.

Creating a Silver Standard for Patent Simplification

“…Most of the current research performs simplification at the sentence level; refer to [10] for a survey. To simplify complex sentences, the applied transformations can be lexical [11] (substituting unusual words or explaining hard concepts) or syntactic (with sentence splitting [12] and other syntactic structure simplification techniques). They can involve removing unimportant information and compressing the text to enhance clarity.…”

Multilingual Lexical Simplification via Paraphrase Generation

“…While previous research primarily focused on English, recent advancements in multilingual and cross-lingual NLP models have facilitated studies in other languages [7,32,27]. This trend is reflected in the Text Simplification, Accessibility, and Readability (TSAR-2022) shared task [31], which provides participants with multilingual LS datasets in three language tracks: English, Spanish, and Portuguese.…”

Prospects for Lexical Simplification: Bibliometric Analysis and New Directions of Research

“…This methodology has been used in studies on disorders including aphasia, [1] [2] non-native speakers [3], dyslexia, [4] and autistic children [5] [6], highlighting the urgent need for text simplification to support these groups. In addition, research on lexical simplification has been conducted by many researchers in various languages, including English [7]- [15] [16], French [17], Spanish [11], [18] [19], Indonesian [20], Malaysian [3], Chinese [21], Portuguese [11], [22].…”