no code implementations • COLING 2022 • Andrew Schneider, Lihong He, Zhijia Chen, Arjun Mukherjee, Eduard Dragut
Word embedding models only include terms that occur a sufficient number of times in their training corpora.
1 code implementation • 22 May 2023 • Bingsheng Yao, Ishan Jindal, Lucian Popa, Yannis Katsis, Sayan Ghosh, Lihong He, Yuxuan Lu, Shashank Srivastava, Yunyao Li, James Hendler, Dakuo Wang
Our AL architecture leverages an explanation-generation model to produce explanations guided by human explanations, a prediction model that utilizes generated explanations toward prediction faithfully, and a novel data diversity-based AL sampling strategy that benefits from the explanation annotations.
no code implementations • 14 Aug 2020 • Lihong He, Chen Shen, Arjun Mukherjee, Slobodan Vucetic, Eduard Dragut
We show that the early arrival rate of comments is the best indicator of the eventual number of comments.
no code implementations • EMNLP 2018 • Shanshan Zhang, Lihong He, Slobodan Vucetic, Eduard Dragut
Finally, a human expert is asked to label a small set of documents and the neural network is fine tuned on those documents.