This course is a graduate introduction to natural language processing - the study of human language from a computational perspective. It covers syntactic, semantic and discourse processing models, emphasizing machine learning or corpus-based methods and algorithms. It also covers applications of these methods and models in syntactic parsing, information extraction, statistical machine translation, dialogue systems, and summarization. The subject qualifies as an Artificial Intelligence and Applications concentration subject.

This is MIT’s introductory course on deep learning methods with applications to computer vision, natural language processing, biology, and more! Students will gain foundational knowledge of deep learning algorithms and get practical experience in building neural networks in TensorFlow. Course concludes with a project proposal competition with feedback from staff and panel of industry sponsors. Prerequisites assume calculus (i.e. taking derivatives) and linear algebra (i.e. matrix multiplication), and we’ll try to explain everything else along the way! Experience in Python is helpful but not necessary.

In this archive there are two activities/assignments suitable for use in a CS0 or Intro course which uses Python.

In the first activity, students are asked to "fill in the code" in a series of short programs that compute a similarity metric (cosine similarity) for text documents. This involves string tokenization, and frequency counting using Python string methods and datatypes.

https://cocalc.com/share/bde99afd-76c8-493d-9608-db9019bcd346/171/Proj1?viewer=share/

In the second activity (taken directly from Think Python 2e) students use a pronunciation dictionary to solve a riddle involving homophones.

https://cocalc.com/share/bde99afd-76c8-493d-9608-db9019bcd346/171/Dicts2?viewer=share/

This OER material was produced as a result of the CS04ALL CUNY OER project

**This resource was published by the News Literacy Project.The News Literacy Project is identified as a “nonpartisan national educational nonprofit” designed to strengthen critical thinking skills and actively seek out credible information. NLP’s strategic framework highlights that in a Stanford History Education Group  research, 96% of high school participants “failed to challenge the credibility of a source.” Additionally, over 50% of high school participants “incorrectly classified evidence as ‘strong.’’ Based on this and other educational research findings, NLP’s aims to advocate and equip educators and learners with programs and resources to promote media literacy. Users have the option of subscribing to NLP to receive up-to-date resources and research that is conducted. Further information can be found here: https://checkology.org/Cost and other restrictions:  This is a free resource. However, to use it, educators and learners will need to provide an email address and other contact information. 

A free quiz developed by the News Literacy project that focuses on combating misinformation on social media platforms.**This resource was published by the News Literacy Project.The News Literacy Project is identified as a “nonpartisan national educational nonprofit” designed to strengthen critical thinking skills and actively seek out credible information. NLP’s strategic framework highlights that in a Stanford History Education Group  research, 96% of high school participants “failed to challenge the credibility of a source.” Additionally, over 50% of high school participants “incorrectly classified evidence as ‘strong.’’ Based on this and other educational research findings, NLP’s aims to advocate and equip educators and learners with programs and resources to promote media literacy. Users have the option of subscribing to NLP to receive up-to-date resources and research that is conducted. Further information can be found here: https://checkology.org/Cost and other restrictions:  This is a free resource. However, to use it, educators and learners will need to provide an email address and other contact information.