Week 1: Computers and Metaphors

Feb 17, 2019

Week 1:

From nearly the very beginning of the Senior Project process, I had a pretty good idea of what I wanted to do my project on. Computer science has been my favorite subject for a long time, and it’s what I want to study when I attend college in the fall–it only seemed logical that I should work on a topic related to my primary field of study. I ultimately decided to work specifically with natural language processing (NLP) when Dr. B. introduced me to my external advisor, Dr. Jelena Mitrovic, a NLP specialist currently researching in Germany.

NLP is fundamentally concerned with the way computers understand human language systems, systems which are extremely complex, intuitive, and flawed. It’s used extensively with AI and other computer systems that interact heavily with humans, and is taking prominence nearly everywhere we look. Apple’s Siri software, for example, uses natural language processing in order to understand us. NLP is also a very new field to me, and I do not have extensive previous experience in the field. Dr. Mitrovic recommended that I research the topic as much as I could before the project actually started, which led me to find interesting research into specifically the computer’s understanding of human metaphor, a topic of research that has become the basis for my own project.

My first week was spent reading “Literal and Distributional Semantics in Compositional Distributional Semantic Models,” the paper that most influenced my topic choice. The main goal of my project is to find a method that most accurately determines whether or not a given phrase is metaphorical or literal–this paper introduced me to the three different methods that I will be analyzing, comparing, and compiling the results of. The paper also introduced me to Compositional Distributional Semantic Models, a model that represents word phrases within a vector space, enabling phrases to be mathematically compared to one another. I intend to further research CDSMs and how to model phrases as vectors, because both of these topics are beyond what I currently know. Nonetheless, the paper was a really interesting read, and I’m excited to see where my project takes me!

2 Replies to “Week 1: Computers and Metaphors”

  1. Anish M. says:

    Very interesting project, Ryan! I’m interested to see where this will take you. Your research so far looks solid.

  2. Shreyas N. says:

    This is a cool project Ryan! I would love to see your progress in this project!

Leave a Reply

Your email address will not be published.