The Wordsmith’s Workshop—Natural Language Processing by DSC
The Data Science Club held an introductory workshop on Natural Language Processing, a subset of artificial intelligence, which involves the computer understanding of human language in its spoken form. The seminar, held on 2nd February, focused on the introduction of text mining and sentence classification using Python and was the club’s first event for the semester.
Following the installation of the required software, the presenters elaborated on the basics of machine learning and the pre-processing of data. The construction of a text processing model for all the participants to implement on their own, along with the use of simple examples and good delivery by the speaker allowed for an intuitive lecture session that explained concepts with clarity. The participants were shown how models are trained and the various steps that go into making them effective, while creating a system to score its reliability in output.
However, the workshop did have its shortcomings. The use of heavy terminology at times and the complexities of Python proved to be daunting to the unfamiliar eye—“I was kind of lost at times. While I understood what the code was doing, I wouldn’t be able to work on it and recreate it myself,” said Sanskaar Sehgal, a first-year student. Additionally, the workshop faced time constraints towards the end as it commenced a little behind schedule.
Despite the rush towards the end, the seminar wound up neatly with the completion of a model capable of distinguishing between positive and negative film reviews with great accuracy. The workshop received a sizable turnout and proved to be a successful affair.
“NLP is a great place to start for people who want to get into the field of AI. It’s more intuitive and easy to work with,” said Arijit Ghosh Chowdhury, a member of DSC’s core committee. This event was a feather in the cap for the club, which envisions itself as a collaborative learning platform for student community growth in the field of data analytics, machine learning and big data.
Image Credits: The Photography Club, Manipal.