Category: Capstone Projects

CDIAL, Google, and UCSC Adapters and Reinforcement Learning for Data-EfficientMachine Translation Student Team: Abigail Kufeldt, Malini Kar, Parikshith Honnegowda, Vignesh S, Pranjali Basmatkar, Shashwat Pandeyand Kushagra Seth[poster] [report] Adobe Enriching Prompts for Text-to-Image Generation using Reinforcement Learning Student Team: Cookie Pan, Haolong Jia, Zoe Gupta, Mridul Pankaj Khanna, Vijay Chilaka, Chengxuan Xia, Sree Latha Chopparapu[poster]…

NLP students showcased their projects at the inaugural NLP Capstone Workshop in August 2021 to an audience made up of faculty members, Industry Advisory Board and invited guests from industry. Each team has half an hour to present their work and take questions from attendees. The NLP Capstone experience offers a great opportunity to extend…

NLP students collaborated with industry mentors from IBM, Interactions, LinkedIn, and Google to develop and implement a variety of Capstone projects to address real-world NLP challenges. The workshop also featured a keynote address about the future of NLP from Professor Ian Lane as well as the annual NLP Industry Panel where leading scientists shared their insights on…

Student Team: Anuroop John Abraham, Archit Bose, Kartik, and Utkarsh Garg Project Mentor: Ashvini Jindal, LinkedIn, Dr. Ananth Sankar, LinkedIn An extensive amount of NLP research focuses on learning word representations that accurately reflect their semantic properties. We investigate whether these word embeddings capture the same semantics of the word as its dictionary definition/gloss. To accomplish this, we leverage a reverse…

Student Team: Brian Mak, Ignacy Tymoteusz Debicki, Juan Sebastian Reyes, and Sriram Mahesh Project Mentor: Professor Yi Zhang (UCSC), Dr. Yueqi Li (X) and Dr. Kezhen Chen (X) We propose a novel visual long-form question answering system for the farming domain, an area of research with no previous baselines or significant work. We scrape and…

Student Team: Anusha Gouravaram, Diji Yang, and Julian Jakob Cremer Project Mentor: Dr. John Chen, Interactions Recent Transformer-type deep neural network models have shown great success in a variety of NLP tasks such as sequence labeling. One sequence tagging task for which work in Transformers is absent is supertagging, which we investigate here. Supertagging, as…

Student team: Anish Kishor Savla, Chih-Kai Ting, Karl Shen Munson, and Serenity Wade Project Mentors: Kiran Kate, IBM Research, Dr. Kavitha Srinivas, IBM Research Style is a significant component of natural language text, able to change the tone of text while keeping the underlying information the same. Even though programming languages have strict rules on…

Student Team: Raghav Chaudhary, Christopher Garcia-Cordova, Kaleen Shrestha, Zachary Sweet Project Mentor: Marina Danilevsky, IBM Research A point has been reached in technological advances where outcomes of important decisions can be determined by the output of a machine​ ​learning model. This has motivated the development of methods that can​ ​generate explanations for these models. However, when…

Student Team: Mamon Alsalihy, Austin King, Nilay Patel Project Mentor: Sarangarajan “Partha” Parthasarathy, Microsoft Modern deep neural networks have immensely powerful predictive power at the cost of equally great size and compute requirements. A lot of recent work has focused on compressing these large models into smaller versions with similar predictive capabilities. Particularly, transformer language…

Student Team: Morgan Eidam, Adam Fidler, John Lara Project Mentor: Arafat Sultan & Radu Florian, IBM; Vittorio Castelli, Amazon Covid-19 has affected the lives of billions globally. Experts were required to make significant decisions affecting hundreds of thousands at a time with limited data. It’s crucial for researchers and the general public to have a…

Student Team: Kit Lao, Alex Lue, Sam Shamsan Project Mentor: Ishan Jindal & Frederick Reiss, IBM In datasets collected from real word data, noise and mislabelings in the corpora are almost always inevitable, and are especially prominent in large datasets. Performance of learned models from these datasets relies heavily on correctly labelled data to produce significant results. This research…