CS224n learning part1

This is the introduction lecture of NLP (Netural language processing)
NLP和深度学习入门。

What’s deep learning?

Deep learning is a subfield of machine learning.

Most machine learning methods work well because of human-designed representations and input features. 大多数机器学习方法都能很好地工作，因为有了人类设计的表示和输入特征。Machine learning becomes just optimizing weights to best make a final prediction.

Representation learning attempts to automatically learning good features or representations 试图自动学习好的特征或表示

Deep learning algorithms attempt to learn (multiple levels of) representation and an output. 深度学习算法试图学习(多级)表示和输出。

Deep NLP = Deep Learning + NLP
combine ideas and goals of NLP with using representation learning and deep learning methods to solve them.

Several big improvements in recent years in NLP with different

• levels: speech, words, syntax, semantics.
• tools: parts of speech, entities, parsing.
• application: machine translation, sentiment analysis, dialogue agents, question answering.

Conclusion: Representation for all levels? Vectors