Workshop on Natural Language Processing with NLTK

1 Leave a comment on paragraph 1 0 On November 17th, I attended my last workshop for the praxis course, the GC Digital Fellows workshop on Natural Language Processing with NLTK. Below is a blurb on the session that can also be found here.

2 Leave a comment on paragraph 2 0 “In this workshop, we will introduce the basics of working with the Natural Language Toolkit, (NLTK), a package for the Python programming language that provides useful tools for text analysis. We will review some of the built in corpora that NLTK provides, and introduce several tools for text analysis (including concordance, conditional frequencies, n-grams, similar words, and part of speech tagging). This workshop is designed for those with a basic knowledge of Python programming.”

3 Leave a comment on paragraph 3 0 We used the following tools: Python 2.7 or Python 3.5, Jupyter Notebook, and The Natural Language Toolkit and its texts. Helpful documentation for this workshop is available here.

4 Leave a comment on paragraph 4 0 I’m not sure I can say that I possess a “basic knowledge of Python programming,” as this workshop required. I’ve certainly attended multiple Python workshops, but I need to at some point sit down and dedicate myself to becoming proficient in this language on my own. I agree with the sentiment raised in one of our class sessions that it would be nice to have a selection of workshops at varying skill levels at the GC. However, there are certainly tons of free resources out there for becoming proficient in things like Python. Also, I think it is sometimes beneficial to be able to dive right in and explore during a workshop and try not to worry about imposter syndrome and so forth. Overall, I think the workshops provided by the GC Digital Fellows are a great resource and that this workshop’s instructors did a great job making what can be an intimidating tool accessible to beginners. The instructors were also highly responsive to technical issues. As with previous GC Digital Fellows workshops I attended, we were encouraged to bring our own laptops. And as with one particular previous workshop, my aging laptop decided to die on me partway through the session, requiring one of the fellows to quickly set up another laptop for me, of which I was very appreciative.

5 Leave a comment on paragraph 5 0 My interest in this workshop was twofold. First, I hope to eventually be able to incorporate text analysis work into my studies as a literature graduate student. Additionally, I believed that this workshop would benefit me in my quest to become proficient in Python in general. I just started a new job at which I deal every day with large quantities of bibliographic and other metadata for a gigantic library system and have been tasked with streamlining the batch management of this metadata. Clearly, becoming proficient in programming would be hugely beneficial in this position. Although I am familiar with many library-centric batch metadata management strategies, I cannot yet be considered a “coder.” After the semester is over I plan to take the next steps necessary to achieving the proficiency needed in these two areas, and this workshop set me on my way.

This entry was posted in Uncategorized. Bookmark the permalink. Both comments and trackbacks are currently closed.

Additional comments powered byBackType

  • Archives

  • Welcome to Digital Praxis 2016-2017

    Encouraging students think about the impact advancements in digital technology have on the future of scholarship from the moment they enter the Graduate Center, the Digital Praxis Seminar is a year-long sequence of two three-credit courses that familiarize students with a variety of digital tools and methods through lectures offered by high-profile scholars and technologists, hands-on workshops, and collaborative projects. Students enrolled in the two-course sequence will complete their first year at the GC having been introduced to a broad range of ways to critically evaluate and incorporate digital technologies in their academic research and teaching. In addition, they will have explored a particular area of digital scholarship and/or pedagogy of interest to them, produced a digital project in collaboration with fellow students, and established a digital portfolio that can be used to display their work. The two connected three-credit courses will be offered during the Fall and Spring semesters as MALS classes for master’s students and Interdisciplinary Studies courses for doctoral students.

    The syllabus for the course can be found at

  • Categories

Skip to toolbar