Ng: Welcome to this first course of NLP in which you’ll learn about classification and vector spaces. You’ll also learn about the application of these ideas to problems like sentiment analysis and word translation. For example, let’s say you have 1,000 product reviews, so pieces of texts written by users. Can you build a system to automatically go through all of these product reviews to figure out what fraction of them are positive reviews versus negative reviews? This course will teach you how. Lucas, can you say a few words about this first course?
Ng: 欢迎来到NLP的第一节课程，你将会学习到分类和向量空间。你也将学习将这些思想应用于情绪分析和单词翻译等问题。例如，假如你有1,000条产品评论，也就是用户写的文章。你能建立一个系统，自动检查所有这些产品评论来计算出正面评论和负面评论的比例吗？这门课会教你如何做。Lucas, 你能简单介绍下第一门课程吗？
Lucas: Sure. In the first week, you’ll learn how to represent text as a vector and build a classifier that will classify whether a sample text is a positive sentiment or a negative one. You will use logistic regression for that. In the second week, you’ll use the Naive Bayes classifier on the same problem.
Lucas: 当然。在第一周，你将会学习如何将文本表示为向量，并构建一个分类器，用于分类示例文本是积极的情绪还是消极的情绪。你将会用到逻辑回归。在第二个周末，在相同的问题上你将会使用朴素贝叶斯分类。
Jonas: In the third week, you’ll learn about vector space models. You’ll learn how to represent text documents like tweets, articles, queries, or any object that contains of text as a vector. This is important in information retrieval, in indexing, in relevancy ranking, and also in information filtering. For example, when you look up a query online, the algorithm relies on all of these concepts to give you back your results. Finally, in week 4, you will build your first simple machine translation system and you’ll make use of locality sensitive hashing to improve the performance of nearest neighbor search.
Jonas: 在第三周，你将会学习向量空间模型。你将会学习如何表示文本(如推特(Twitter)、文章、查询)或者包含文本的对象表示为向量。这在信息检索、索引、相关性排名以及信息过滤中都很重要。例如，当你在线查询时，算法依赖于这些概念返回到你的结果中。最后，在第四周，你将会建立你的第一个简单的机器翻译系统，你将会使用局部敏感哈希(LSH)来提高最近邻搜索的性能。
Ng: Thanks, Jonas and Lucas.
Ng: 感谢Jonas和Lucas。