no code implementations • 31 Jan 2024 • Rheeya Uppaal, Yixuan Li, Junjie Hu
In this work, we evaluate the utility of CPT for generative UDA.
no code implementations • 16 Nov 2023 • Yun-Shiuan Chuang, Yi Wu, Dhruv Gupta, Rheeya Uppaal, Ananya Kumar, Luhang Sun, Makesh Narsimhan Sreedhar, Sijia Yang, Timothy T. Rogers, Junjie Hu
Adapting pre-trained language models (PLMs) for time-series text classification amidst evolving domain shifts (EDS) is critical for maintaining accuracy in applications like stance detection.
1 code implementation • 22 May 2023 • Rheeya Uppaal, Junjie Hu, Yixuan Li
Fine-tuning with pre-trained language models has been a de facto procedure to derive OOD detectors with respect to in-distribution (ID) data.
no code implementations • ACL 2021 • Ahsaas Bajaj, Pavitra Dangati, Kalpesh Krishna, Pradhiksha Ashok Kumar, Rheeya Uppaal, Bradford Windsor, Eliot Brenner, Dominic Dotterrer, Rajarshi Das, Andrew McCallum
Abstractive summarization is the task of compressing a long document into a coherent short document while retaining salient information.
no code implementations • 17 Nov 2019 • Haw-Shiuan Chang, Shankar Vembu, Sunil Mohan, Rheeya Uppaal, Andrew McCallum
Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks.
no code implementations • 15 Sep 2019 • Rheeya Uppaal
Existing non-adversarial methods learn mappings between the source and target domains, to achieve reasonable performance.
no code implementations • 30 Apr 2019 • Bhanu Pratap Singh, Iman Deznabi, Bharath Narasimhan, Bryon Kucharski, Rheeya Uppaal, Akhila Josyula, Madalina Fiterau
Vertical FIT (FIT-V) is a variant of FIT which also models the relationship between different temporal signals while creating the informative dense representations for the signal.