Focus on cutting-edge technology research and application implementation in the fields of supervised learning and NLP. 将这句话拆成三句英文，并扩写。

1. The focus is on researching cutting-edge technology in the fields of supervised learning and NLP.
2. A major emphasis is placed on the implementation of these technologies in real-world applications.
3. The goal is to continue pushing the boundaries of what is currently possible with these techniques in order to improve their performance and effectiveness.

相关问题

Train set/test set: We would like to point out that most prior work in unsupervised classification use both the train and test set during training. We believe this is bad practice and therefore propose to only train on the train set. The final numbers should be reported on the test set (see table 3 of our paper). This also allows us to directly compare with supervised and semi-supervised methods in the literature. We encourage future work to do the same. We observe around 2% improvement over the reported numbers when including the test set. Reproducibility: We noticed that prior work is very initialization sensitive. So, we don't think reporting a single number is therefore fair. We report our results as the mean and standard deviation over 10 runs. Please follow the instructions underneath to perform semantic clustering with SCAN.，这段话是什么意思

这段话是在介绍一个名为SCAN的无监督分类方法的实验设置和结果报告。其中，作者指出之前的一些无监督分类方法在训练时同时使用了训练集和测试集，这种做法是不好的，因为会导致模型泛化能力的过度估计。因此，作者建议只在训练集上进行训练，并在测试集上报告最终结果，以便与其他监督和半监督方法进行比较。作者还观察到，之前的一些方法非常依赖于初始化，因此为了保证结果的可重复性，作者进行了10次实验，并报告了平均值和标准差。最后，作者提供了使用SCAN进行语义聚类的指南。

请将以下内容进行压缩凝练（注意：可对内容进行删减，对错误进行修正，对语句顺序进行调整，符合美式英语标准，符合英语母语者语言习惯，句子简明易懂，术语使用准确，保留文章结构、不偏离论文主要内容）： Traditional machine learning methods can be divided into two categories: supervised and unsupervised learning methods. The supervised learning methods include Support Vector Machine (SVM), Random Forest, Decision Tree, etc. The unsupervised learning methods include Principal Component Analysis (PCA), Independent Component Analysis (ICA), K-means clustering, Non-Negative Matrix Decomposition (NMF), etc. Traditional machine learning methods also have shortcomings, which require high data quality, professional processing and feature engineering of data by experts according to experience and expertise, and high labor cost. At the same time, the use of traditional machine learning methods have its limitation because they need to be combined with the geological situation of a certain region to target anomaly detection, and cannot be universally applied to other regions.

Traditional machine learning can be divided into supervised and unsupervised methods, such as Support Vector Machines, Random Forests, Decision Trees, Principal Component Analysis, Independent Component Analysis, K-means clustering, and Non-Negative Matrix Decomposition. However, these methods have limitations and require high-quality data, expert feature engineering, and are often region-specific for anomaly detection.