ml-basics.4 - Natural Language Processing Natural Language Processing Machine Learning for NLP Machine Learning(ML Basics Supervised machine learning

ml-basics.4 - Natural Language Processing Natural Language...

This preview shows page 1 - 2 out of 5 pages.

Natural Language Processing 1 Machine Learning for NLP Until the early 1990’s, NLP systems were built manually with hand-crafted dictionaries and rules. Manually creating systems is time-consuming and requires linguistic expertise. Humans are especially prone to errors of omission. As large electronic text corpora became increasingly available, researchers began using machine learning techniques to automatically build NLP systems. Today, the vast majority of NLP systems use machine learning! ML-based NLP systems are generally more robust (less fragile) and have good coverage, when sufficiently trained. Natural Language Processing 2 Machine Learning (ML) Basics Supervised machine learning begins with training data , which are examples that have been labelled (“annotated”) by a person with the correct answers. To train a part-of-speech tagger, a human would label each word with its correct part-of-speech in sample texts. To train a parser, a human would generate the correct parse tree for each sentence in sample texts. The ML algorithm learns how to solve the problem using the labelled examples. The more training data, the better! The training texts should be the same kind of texts that the NLP system will be expected to process when it is deployed! Natural Language Processing 3 Data Sets Used for Experimentation To determine how well an NLP system performs, you also need labelled data. So the annotated texts are usually divided into 3 subsets: Training Set: Data used to train the ML algorithm. The developer may also look at this data to help design the system. This is usually the largest subset. Tuning Set: Data set aside to assess how well the program performs on unseen data and/or to set parameters. Helps to minimize overfitting .
Image of page 1
Image of page 2

You've reached the end of your free preview.

Want to read all 5 pages?

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Stuck? We have tutors online 24/7 who can help you get unstuck.
A+ icon
Ask Expert Tutors You can ask You can ask You can ask (will expire )
Answers in as fast as 15 minutes
A+ icon
Ask Expert Tutors