Title: Natural Language Processing for Unstructured Text in Colloquial Conversations (tentative)
Mentor: Francesco Lelli
Have you ever received an eMail from a friend proposing a vacation to Venice and 30 second later you stumble into an advertisement proposing cheap flights or hotels for that very same destination? Welcome to the world of Natural Language Processing (NLP).
This thesis will investigate the limits that machines have in processing and understanding colloquial conversations. If you are curious to know what can actually be automatized by Artificial Intelligence this thesis is for you.
You will be able to touch with your own hands the technological and business limits that this technology is facing in its adoption into our everyday life as well as propose your personal ideas for improving the present state of the art.
Moreover, you will have the opportunity to master techniques of NLP for parsing and extracting semantic information from any kind of text.
Your claims will be validated using popular NLP libraries (yes, you will have to write a few line of code!) using an existing dataset as benchmark (no, you do not have to collect data!).
If you are curious and you what to know more about the topic, I recommend you the following:
- A generic article in Wikipedia about Natural Language Processing: https://en.wikipedia.org/wiki/Natural_language_processing
- Watch this YouTube video (knowledge of Python will help you in understanding it)
- A few keywords that you may want to use in google scholar: natural language processing, NLP topic modelling, natural language processing interview, natural language processing data.
This project does not involve an internship. Instead, it will try to have a high academic relevance and theoretical contribution and, based on the quality of your work the candidate may be able to publish the results in the proceedings and scientific journals. If this topic triggers your intellectual curiosity, let me know.
If you are interested in the topic, do not hesitate to contact us for more information.
