Computational Linguistics with Advanced Python

Welcome to Computational Linguistics with Advanced Python, ANLY 521 / LING 472, with Professor Elizabeth Merkhofer (emm228@georgetown.edu).

We meet Thursdays 11:00 - 1:30 in ICC 102.

Office Hours

Professor: Virtual, Mondays 9-12 AM

Please email ahead of time so we can set up a Zoom meeting. If you’d prefer to meet face-to-face, I’m happy to arrange a time before or after class on Thursday.

TA:

Graduate Student Lounge, Car Barn 100: Tuesdays 1:30-3:00 PM

ICC ground floor: Wednesdays 2-3 PM

Course Objectives

Strengthen Python skills through computational linguistics applications. Learn to collect, parse, and model natural language data, both noisy (“from the wild”) and annotated for the scientific community. Rigorously evaluate systems to understand performance.

Unit 1: Author ID

Supervised learning: data practices

Naive Bayes model

Features for text

Scraping your own dataset

Unit 2: Semantic Similarity

Edit distance

Logistic Regression model

Out-of-domain challenges

Neural features in non-neural models

Unit 3: Named Entity Recognition

Conditional Random Fields model

Reading complex data formats

Linguistic resources

Contact

Please email with questions. I'm happy to set up a meeting.

For questions on homework, cc our teaching assistant, Yan Liu: yl1023@georgetown.edu