Petros Kaklamanis, COL ’24, Athens, Greece
During the summer I worked as an intern at the Computational Communicative Development Lab (CoCoDev) which is part of the Aix-Marseille University (Marseille, France).
As an intern at the Computational Communicative Development Lab, I was involved in activities related to the computational modeling of children’s communicative and cognitive development. We used Machine Learning computational models to analyze children’s developing grammatical skills from naturalistic child-caregiver dialog as recorded on the CHILDES corpus. I learned to preprocess language data in order to use them for automated processes which are able to spot communicative feedback in conversations, and thus annotate a corpus of around 10,000 dialogue entries. The annotation process involved categorizing ungrammatical utterances depending on the syntactic and morphological nature of the child’s linguistic mistake. The annotation and processing of large data helps in better understanding the corrections that caregivers give their children on a daily basis when they make linguistic mistakes. Studying these corrections helps us understand the role of child-caregiver interaction in child acquisition. During this experience, I also learned to design and implement Machine Learning algorithms using Python and Pytorch for research in language processing, building on the skills I acquired in my related machine learning class at Penn.
This internship was a great opportunity to obtain experience in Cognitive Science research. In particular, I was able to combine the skills I have acquired in my two majors, Cognitive Science and Computer Science. A significant part of my coursework is related to computational and linguistics topics, which I have long wanted to use in a research setting. I was very glad to have worked with the team as we will continue cooperating over the Fall semester. The paper that we will publish will also help me understand how the preparation, submission, and review process of Cognitive Science works. Further, the opportunity allowed me to interact and learn from members of a different institution, and of different countries, which provided me with the essential exposure to a more diverse set of coworkers, research ideas, and collaboration skills.
This is part of a series of posts by recipients of the 2023 Career Services Summer Funding Grant. We’ve asked funding recipients to reflect on their summer experiences and talk about the industries in which they spent their summer. You can read the entire series here
