Reminder: ?Meeting hosts only admit guests that they know to the Zoom meeting. Hence, you're highly encouraged to use your USC account to sign into Zoom. If you're an outside visitor, please inform [email protected] beforehand so we'll be aware of your attendance and let you in.
Abstract: I will present two works on controlled generation, with a shared theme of using predictors to guide a generator. Future Discriminators for Generation (FUDGE) is a flexible and modular method for controlled text generation, which learns an attribute predictor operating on a partial sequence, and uses this predictor's outputs to adjust a base generator's original probabilities with no need for re-training or fine-tuning. Switching domains, I will also present Improving Molecular Design by Stochastic Iterative Target Augmentation, a self-training approach for using a strong attribute predictor to guide the training of a generator in a semi-supervised manner. Overall, we find that these predictor-guided approaches to controlled generation substantially outperform prior methods in several text generation tasks, as well as in molecular design and program synthesis.
Bio: Kevin Yang is a rising third-year PhD student at UC Berkeley advised by Dan Klein within Berkeley NLP and BAIR. He is broadly interested in AI in the context of language and game-playing, particularly in designing more modular and/or language-controllable agents. He is also interested in neural architectures for structured domains such as chemistry. Previously, Kevin worked with Regina Barzilay during his undergrad and M.Eng. at MIT, on natural language processing and chemistry applications of deep learning, especially graph convolutional networks.
The recording for this talk will be posted on our USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI
Subscribe here to learn more about upcoming seminars: https://www.isi.edu/events/