基于复述生成的多语言词汇简化
Multilingual Lexical Simplification via Paraphrase Generation
AI总结：
本文提出一种基于复述生成的多语言词汇简化方法，将复述视为零样本翻译任务，通过仅关注复杂词词汇变化的新颖解码策略生成替代词，在英语、西班牙语和葡萄牙语上显著优于BERT和零样本GPT3方法。
摘要：
基于预训练语言模型的词汇简化（LS）方法取得了显著进展，通过分析上下文为复杂词生成潜在替代词。然而，这些方法需要为不同语言分别建立预训练模型，且忽略了句子意义的保留。本文提出一种基于复述生成的多语言LS新方法，因为复述在保留句子意义的同时提供了词汇选择的多样性。我们将复述视为支持数百种语言的多语言神经机器翻译中的零样本翻译任务。将输入句子送入复述建模的编码器后，我们基于一种仅关注复杂词词汇变化的新颖解码策略生成替代词。实验结果表明，我们的方法在英语、西班牙语和葡萄牙语上显著优于基于BERT的方法和零样本GPT3方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
