Semester.ly

Johns Hopkins University | EN.600.465

Natural Language Processing

3.0

credits

Average Course Rating

(4.68)

This course is an in-depth overview of techniques for processing human language. How should linguistic structure and meaning be represented? What algorithms can recover them from text? And crucially, how can we build statistical models to choose among the many legal answers? The course covers methods for trees (parsing and semantic interpretation), sequences (finite-state transduction such as morphology), and words (sense and phrase induction), with applications to practical engineering tasks such as information retrieval and extraction, text classification, part-of-speech tagging, speech recognition and machine translation. There are a number of structured but challenging programming assignments. [Applications] Recommended Course Background: EN.600.226

Fall 2012

(4.86)

Fall 2013

(4.61)

Fall 2014

(4.56)

Fall 2012

Professor: Jason Eisner

(4.86)

Students said the professor was a great teacher who was passionate about the subject and very wil ing to help students with any questions they had. They did not like the very heavy workload. Students suggested reducing some of the assignments or making the class worth more credits to compensate for the high workload. Overall, students recommended this as a very rewarding class, but say prospective students should be prepared to spend a lot of time on the homework and studying for exams.

Fall 2013

Professor: Jason Eisner

(4.61)

Students thought that the best aspects of this course included the professor’s teaching style and his clear enthusiasm for the subject. Students found that the materials were interesting, and that the assignments helped students get hands-on experience. The workload was rather heavy and difficult and students often found that the assignments often took much longer than they needed to be. Suggestions for improvement included creating shorter, more concise homework assignments and lightening the workload over the course of the semester. Prospective students should be aware of the heavy workload, but know that they will learn a lot over the semester. They should have a strong programming background, and be prepared to allot a fair amount of time to complete the various assignments.

Fall 2014

Professor: Jason Eisner

(4.56)

Students thought the best aspect of this course was the effective teaching of the engaging instructor who taught a comprehensive introduction to the subject matter. Students expressed that their least favorite aspect of the course was the heavy workload of homework assignments. Some students thought the course could be improved by reducing the workload or by reducing the topics covered and even expanding the class to two semesters. They thought it was most important for others considering taking the class to know that the course required a substantial time commitment and that they should only take the class alongside classes with light workloads.