no code implementations • 29 Jan 2023 • Abhijit Mahabal, Jiyun Luo, Rui Huang, Michael Ellsworth, Rui Li
Creating a taxonomy of interests is expensive and human-effort intensive: not only do we need to identify nodes and interconnect them, in order to use the taxonomy, we must also connect the nodes to relevant entities such as users, pins, and queries.
no code implementations • 20 Jun 2020 • Abhijit Mahabal, Yinrui Li, Rajat Raina, Daniel Sun, Revati Mahajan, Jure Leskovec
Identifying unsafe queries is necessary to protect users from inappropriate query suggestions.
no code implementations • NAACL 2019 • Abhijit Mahabal, Jason Baldridge, Burcu Karagol Ayan, Vincent Perot, Dan Roth
Training data for text classification is often limited in practice, especially for applications with many output classes or involving many related classification problems.
1 code implementation • ACL 2019 • Yanai Elazar, Abhijit Mahabal, Deepak Ramachandran, Tania Bedrax-Weiss, Dan Roth
Most current NLP systems have little knowledge about quantitative attributes of objects and events.
no code implementations • SEMEVAL 2018 • Abhijit Mahabal, Dan Roth, Sid Mittal
Words are polysemous and multi-faceted, with many shades of meanings.