1 code implementation • LREC 2022 • Hrishikesh Kulkarni, Sean MacAvaney, Nazli Goharian, Ophir Frieder
To complement this evaluation, we propose a dynamic thresholding technique that adjusts the classifier’s sensitivity as a function of the number of posts a user has.
no code implementations • 31 Jul 2023 • Hrishikesh Kulkarni, Sean MacAvaney, Nazli Goharian, Ophir Frieder
We introduce 'LADR' (Lexically-Accelerated Dense Retrieval), a simple-yet-effective approach that improves the efficiency of existing dense retrieval models without compromising on retrieval effectiveness.
no code implementations • 16 Jun 2021 • Hrishikesh Kulkarni, Bradly Alicea
This can be used to create personalized clusters of book titles of interest to readers.
1 code implementation • 2 Jun 2021 • Zhiwen Tang, Hrishikesh Kulkarni, Grace Hui Yang
Many task-oriented dialogue systems use deep reinforcement learning (DRL) to learn policies that respond to the user appropriately and complete the tasks successfully.
no code implementations • 14 Oct 2019 • Hrishikesh Kulkarni, P Joshi, P Chande
The emotional impact of the news title on reader is one of the most important factors.
no code implementations • 1 Aug 2019 • Hrishikesh Kulkarni, Bradly Alicea
The association among corresponding node and core nodes is used for the same.
BIG-bench Machine Learning Cultural Vocal Bursts Intensity Prediction