no code implementations • NAACL (ACL) 2022 • Weiyi Lu, Sunny Rajagopalan, Priyanka Nigam, Jaspreet Singh, Xiaodi Sun, Yi Xu, Belinda Zeng, Trishul Chilimbi
However, one issue that often arises in MTL is the convergence speed between tasks varies due to differences in task difficulty, so it can be a challenge to simultaneously achieve the best performance on all tasks with a single model checkpoint.
no code implementations • 7 Jun 2022 • Xiaodi Sun, Sunny Rajagopalan, Priyanka Nigam, Weiyi Lu, Yi Xu, Belinda Zeng, Trishul Chilimbi
In this paper, we propose an improvement to prompt-based fine-tuning that addresses these two issues.
no code implementations • 12 Oct 2021 • Vihan Lakshman, Choon Hui Teo, Xiaowen Chu, Priyanka Nigam, Abhinandan Patni, Pooja Maknikar, SVN Vishwanathan
When training a dyadic model, one seeks to embed two different types of entities (e. g., queries and documents or users and movies) in a common vector space such that pairs with high relevance are positioned nearby.
1 code implementation • 1 Jul 2019 • Priyanka Nigam, Yiwei Song, Vijai Mohan, Vihan Lakshman, Weitian, Ding, Ankit Shingavi, Choon Hui Teo, Hao Gu, Bing Yin
To address these issues, we train a deep learning model for semantic matching using customer behavior data.