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 your networks and put yourself in front of potential employers. Registration is open to the professional NLP community and invitations are sent to a range of interested parties who are able to attend either in person or remotely.
-
Informers: Evaluating Explanation Quality
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…
-
MKD-Ultra: Compressing Causal Language Models in Multiple Steps
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…
-
Domain Adaptation for Question Answering on COVID-19
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…
-
Identifying Errors in SRL using Weak Supervision
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…
-
Amazon Alexa Prize Discourse Model & Coreference Resolution
The goal of the project was to create a coreference resolution model that could identify entities being referred to in a social bot’s user utterance using information found in our discourse model. This was addressed by implementing both a rule-based, neural, and ensemble model, and comparing how these performed on a set of pronominal types:…
-
Information Extraction of Corporate Events from the Web
Student Team: Tianxiao Jiang, David Li, Liren Wu Project Mentor: Yuval Marton & Swapnil Khedekar, Bloomberg Publicly traded companies are required to report earnings and hold certain types of events. During these events stocks are most volatile and draw huge interest from analysts, investors, shareholders and journalists. Consequently, the collection of this information is valuable,…