论文标题
从Freem到D'Anembert：一个大型语料库和早期现代法语的语言模型
From FreEM to D'AlemBERT: a Large Corpus and a Language Model for Early Modern French
论文作者
论文摘要
语言历史状态的语言模型对于允许对旧文本来源的最佳数字化和分析变得越来越重要。由于这些历史状态同时更加复杂，并且在可用的语料库中更稀缺，因此需要具体的努力来训练自然语言处理（NLP）工具适应数据。在本文中，我们介绍了为早期现代法语开发NLP工具的努力（历史法语（从16 $^\ text {th} $到18 $^\ text {th} $百年）。我们介绍$ \ text {freem} _ {\ text {max}} $现代法语和d'Alembert的语料库，这是一种基于Roberta的语言模型，对$ \ text {freem} _ {\ text {max {max}} $进行了训练。我们通过将D'Alembert在言论一部分标记任务上进行微调来评估D'Alembert的有用性，从而优于先前的测试集上的工作。重要的是，我们找到了语言模型转移学习能力的证据，因为它在资源较低的时间段上的表现似乎已被更多的资源增强。我们发布$ \ text {freem} _ {\ text {max}} $ colpus的d'Alembert和$ \ text {freem} _ {freem}的开源子部分。
Language models for historical states of language are becoming increasingly important to allow the optimal digitisation and analysis of old textual sources. Because these historical states are at the same time more complex to process and more scarce in the corpora available, specific efforts are necessary to train natural language processing (NLP) tools adapted to the data. In this paper, we present our efforts to develop NLP tools for Early Modern French (historical French from the 16$^\text{th}$ to the 18$^\text{th}$ centuries). We present the $\text{FreEM}_{\text{max}}$ corpus of Early Modern French and D'AlemBERT, a RoBERTa-based language model trained on $\text{FreEM}_{\text{max}}$. We evaluate the usefulness of D'AlemBERT by fine-tuning it on a part-of-speech tagging task, outperforming previous work on the test set. Importantly, we find evidence for the transfer learning capacity of the language model, since its performance on lesser-resourced time periods appears to have been boosted by the more resourced ones. We release D'AlemBERT and the open-sourced subpart of the $\text{FreEM}_{\text{max}}$ corpus.
