1 code implementation • 9 Mar 2024 • Lorenzo Jaime Yu Flores, Arman Cohan
We study the behavior of the underlying losses between factual and non-factual examples, to understand and refine the performance of LT. We demonstrate that LT's performance is limited when the underlying assumption that noisy targets have higher NLL loss is not satisfied, and find that word-level NLL among entities provides better signal for distinguishing factuality.
1 code implementation • 17 Oct 2023 • Lorenzo Jaime Yu Flores, Heyuan Huang, Kejian Shi, Sophie Chheang, Arman Cohan
Text simplification has emerged as an increasingly useful application of AI for bridging the communication gap in specialized fields such as medicine, where the lexicon is often dominated by technical jargon and complex constructs.
1 code implementation • 6 Feb 2023 • Yilun Zhao, Zhenting Qi, Linyong Nan, Lorenzo Jaime Yu Flores, Dragomir Radev
Logical Table-to-Text (LT2T) generation is tasked with generating logically faithful sentences from tables.
1 code implementation • 6 Oct 2022 • Lorenzo Jaime Yu Flores, Dragomir Radev
With 84. 75 million Filipinos online, the ability for models to process online text is crucial for developing Filipino NLP applications.
1 code implementation • 25 May 2022 • Linyong Nan, Lorenzo Jaime Yu Flores, Yilun Zhao, Yixin Liu, Luke Benson, Weijin Zou, Dragomir Radev
Unfaithful text generation is a common problem for text generation systems.
1 code implementation • AAAI Workshop AdvML 2022 • Lorenzo Jaime Yu Flores, Yiding Hao
With the proliferation of online misinformation, fake news detection has gained importance in the artificial intelligence community.