# Multilingual Lexical Simplification via Paraphrase Generation

arXiv: https://arxiv.org/abs/2307.15286 · HTML: https://mlsanity.com/paper/2307.15286/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 40 references that are in the map.
- First posted on arXiv 28 Jul 2023.

## Builds on (most cited first, 18 of 18)

- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [Multilingual Neural Machine Translation with Language Clustering](https://mlsanity.com/paper/1908.09324/) (2019)
- [ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-constrained Neural Machine Translation](https://mlsanity.com/paper/1901.03644/) (2019)
- [Paraphrase Generation as Zero-Shot Multilingual Translation: Disentangling Semantic Similarity from Lexical and Syntactic Diversity](https://mlsanity.com/paper/2008.04935/) (2020)
- [Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss](https://mlsanity.com/paper/1902.09191/) (2019)
- [Token-level Adaptive Training for Neural Machine Translation](https://mlsanity.com/paper/2010.04380/) (2020)
- [Findings of the TSAR-2022 Shared Task on Multilingual Lexical Simplification](https://mlsanity.com/paper/2302.02888/) (2023)
- [Lexical Simplification Benchmarks for English, Portuguese, and Spanish](https://mlsanity.com/paper/2209.05301/) (2022)
- [UniHD at TSAR-2022 Shared Task: Is Compute All We Need for Lexical Simplification?](https://mlsanity.com/paper/2301.01764/) (2023)
- [Strong Baselines for Complex Word Identification across Multiple Languages](https://mlsanity.com/paper/1904.05953/) (2019)
- [Chinese Lexical Simplification](https://mlsanity.com/paper/2010.07048/) (2020)
- [Unsupervised Lexical Substitution with Decontextualised Embeddings](https://mlsanity.com/paper/2209.08236/) (2022)
- [NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures](https://mlsanity.com/paper/2204.13692/) (2022)
- [MANTIS at TSAR-2022 Shared Task: Improved Unsupervised Lexical Simplification with Pretrained Encoders](https://mlsanity.com/paper/2212.09855/) (2022)
- [Improving Contextual Representation with Gloss Regularized Pre-training](https://mlsanity.com/paper/2205.06603/) (2022)

## Built on by (most cited first, 1 of 1)

- [Readability-guided Idiom-aware Sentence Simplification (RISS) for Chinese](https://mlsanity.com/paper/2406.02974/) (2024)

## Abstract (arXiv)

Lexical simplification (LS) methods based on pretrained language models have made remarkable progress, generating potential substitutes for a complex word through analysis of its contextual surroundings. However, these methods require separate pretrained models for different languages and disregard the preservation of sentence meaning. In this paper, we propose a novel multilingual LS method via paraphrase generation, as paraphrases provide diversity in word selection while preserving the sentence's meaning. We regard paraphrasing as a zero-shot translation task within multilingual neural machine translation that supports hundreds of languages. After feeding the input sentence into the encoder of paraphrase modeling, we generate the substitutes based on a novel decoding strategy that concentrates solely on the lexical variations of the complex word. Experimental results demonstrate that our approach surpasses BERT-based methods and zero-shot GPT3-based method significantly on English, Spanish, and Portuguese.