אירועים והרצאות בפקולטה למדעי המחשב ע"ש הנרי ומרילין טאוב

Domain adaptation setups were not all born equal, and some domains are easier to adapt to and from than others. This talk will show and attempt to estimate the difficulty (or ease) of adapting between different domains, based on the causal effect of certain features in the data on the adapting model’s predictions. This question is relevant in many real-life scenarios where computational resources exist in relative abundance, while labeling and data-gathering is time-consuming, expensive or otherwise problematic. We will discuss approaches to inspecting NLP models, leveraging existing labeled and unlabeled data which might not seem immediately relevant, and trying to reason about the factors which affect NLP model performance. Short bio: Boaz is a graduate student on Professor Roi Reichart’s research group, interested in representation learning and domain adaptation, as well as leveraging outside knowledge in existing ML ideas.