Join us as Hamed Zamani, PhD Candidate at University of Massachusetts Amherst, presents "Neural Information Retrieval without Labeled Data."
Information access systems, including search engines, question answering, and recommender systems, have made significant impacts on people's daily lives. In addition to the complexity of understanding user information needs and satisfactions, this is mainly due to the lack of large-scale training data and task-specific neural architectures for information access. To address these issues, Zamani will introduce weak supervision for training information access models that has opened a new direction by laying the groundwork for cutting edge machine learning research in information access systems.
Refrehments at 10:00am
Monday, February 4 at 10:30 a.m. to 11:30 a.m.