I will work on NLP 100 Exercise 2020 (Rev 2).
NLP 100 Exercise is a bootcamp designed for learning skills for programming, data analysis, and research activities by taking practical and exciting assignments.
If you find something wrong in my code or something that can be rewritten, please keep pointing it out to me.
Review advanced but important topics of programming, handling strings and text.
Experience useful UNIX tools for research and data analysis. Improve programming skills and realize the ecosystem of existing tools by implementing these tools.
Extract various information and knowledge by applying regular expressions to Wikipedia markups.
Obtain statistics of the word usage of the novel, “Alice’s Adventures in Wonderland,” by applying a part-of-speech tagger
Experience analysis and access to dependency trees by applying a dependency parser to the novel, “Alice’s Adventures in Wonderland.”
Build a document classifier based on machine learning. In addition, learn the evaluation methodology for machine learning.
Learn the usage of word embeddings by computing the similarity between words and word analogy. In addition, experience clustering and visualization of word embeddings.
Learn the usage of a deep-learning framework, and implement a document classifier based on Neural Network models.
Implement Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs) by using a deep-learning framework.
Build a neural machine translation by using an existing tool.
言語処理100本ノック 2020に取り組みます。 間違っているコードの指摘や、もっと良い書き方の提案などぜひコメントでお願いします。