摘要
机器人与机器学习每日新闻的一位新闻记者兼新闻编辑发表了关于人工智能的新研究结果。根据比利时根特的新闻报道，B y NewsRx编辑，研究称，"在本文中，我们将说明根特大学亚述学家和计算语言学家之间的合作，该合作建立了一项试点研究，使用自然语言处理(NLP)技术分析旧巴比伦(OB)字母中使用的语言。"这项研究的财政支持者包括Beslpo。新闻记者从根特大学的研究中获得了一句话：“OB字母构成了一个有趣的数据集，因为(1)它们构成了日常方言的宝贵来源，(2)已经记录了5000多封，其中许多可以通过Altbabylonische Brief系列和楔形数字图书馆倡议进行音译和翻译。基于OB Sippar的第一批信件，后来又被其他阿卡德字母扩展。我们的目标是开发机器学习方法来执行字母的半自动文本分析和注释。我们将在这里使用机器学习提出一个部分-SP ECH(PoS)标签预测模型。输入数据是Akkadi An音译，性能最好的模型是一个微调的多语言BERT转换器，带有单词嵌入(加权平均F1:90.19%)。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New study results on artificial intell igence have been published. According to news reporting out of Ghent, Belgium, b y NewsRx editors, research stated, “Within this paper we will account for a coop eration between Ghent University based Assyriologists and computational linguist s that has set up a pilot study to analyse the language used in Old Babylonian ( OB) letters using Natural Language Processing (NLP) techniques.” Financial supporters for this research include Beslpo. The news correspondents obtained a quote from the research from Ghent University : “OB letters make up an interesting dataset because (1) they form an invaluable source for everyday vernacular language, and (2) more than 5000 have been recov ered, many of which are accessible in transliteration and translation through th e series Altbabylonische Briefe and the Cuneiform Digital Library Initiative. Ba sed on a first batch of letters from OB Sippar, later extended by other Akkadian letters, we aim to develop machine learning approaches to perform semi-automati c text analysis and annotation of the letters. We will here present a Part-of-Sp eech (PoS) tag prediction model using machine learning. The input data is Akkadi an in transliteration and the best performing model is a fine-tuned Multilingual BERT Transformer with Word embeddings (weighted avg F1: 90.19 %).”
NETL
NSTL